G10L  13/00  \	0	0	5D045	G10L  13/00	13	ιƥȤѴ륷ƥΣ	Speech synthesis; Text to speech systems [7]
G10L  13/00 100 \	1	1	5D045	G10L  13/00	4	ѤŬѤ˴ؤ	Relating to applying voice synthesis technique
G10L  13/00 100 A	1	0	5D045	G10L  13/00	526	ޤϥ	Toy and game
G10L  13/00 100 B	1	0	5D045	G10L  13/00	200	ХޤŻҥ֥å	Album and electronic book
G10L  13/00 100 C	1	0	5D045	G10L  13/00	1712	ɤޤϷ	Guide and alarm
G10L  13/00 100 D	1	0	5D045	G10L  13/00	23	ɣå	IC tag
G10L  13/00 100 E	1	0	5D045	G10L  13/00	387	פޤα	Clock and answering machine
G10L  13/00 100 F	1	0	5D045	G10L  13/00	54	ץåȥۡޤϱع	Platform or station premises
G10L  13/00 100 G	1	0	5D045	G10L  13/00	402		Translation
G10L  13/00 100 H	1	0	5D045	G10L  13/00	645	ʥ	Car navigation system
G10L  13/00 100 J	1	0	5D045	G10L  13/00	458	ۡڡ᡼ޤʸ	Homepage, E-mail and teletext
G10L  13/00 100 K	1	0	5D045	G10L  13/00	881	ʸɤ߾夲	Reading out apparatus of document or the like
G10L  13/00 100 L	1	0	5D045	G10L  13/00	802	ǧ	Recognition apparatus
G10L  13/00 100 M	1	1	5D045	G10L  13/00	1888		Conversation apparatus
G10L  13/00 100 P	1	0	5D045	G10L  13/00	14	ɽ֡ȷɽǣ̣	Display (Displaying waveform : G10L21/06)
G10L  13/00 100 Q	1	1	5D045	G10L  13/00	67	ɽƤ˴ؤ	Relating to display contents
G10L  13/00 100 R	1	2	5D045	G10L  13/00	493	Ϥ벻ƱƥȤϤ	Output the same text as output voice information
G10L  13/00 100 S	1	2	5D045	G10L  13/00	497	Ϥ벻˴ϢϤ	Output image or the like related to output voice
G10L  13/00 100 U	1	1	5D045	G10L  13/00	55	Ƥħ	Characterized by processing contents
G10L  13/00 100 V	1	2	5D045	G10L  13/00	285	ɽޤϱȤƱ	Synchronization with displayed picture or image
G10L  13/00 100 Y	1	0	5D045	G10L  13/00	541		singing voice synthesis
G10L  13/00 100 Z	1	0	5D045	G10L  13/00	736	¾֤ŬѤ	Application to other apparatus
G10L  13/02  \	1	1	5D045	G10L  13/02	12	ˡΣ	Methods for producing synthetic speech; Speech synthesisers [7,2013.01]
G10L  13/02 110 \	2	2	5D045	G10L  13/02	0	˴ؤϤ˴ؤ	Relating to input of information concerning synthetic sound
G10L  13/02 110 A	2	0	5D045	G10L  13/02	117	ܡ	Keyboard
G10L  13/02 110 B	2	0	5D045	G10L  13/02	210	ĻǵϿΡ㡥С	Being recorded by visible information [Bar code or the like]
G10L  13/02 110 C	2	0	5D045	G10L  13/02	95	Ϥ줿ܥб벻ϤΡ㡥Ȥ߹碌뤳ȤˤɤΤ褦ʲǤϲǽʤ	Phoneme or the like being outputted corresponding to input button [Capable of output as any sound according to the combination of the pressing operations]
G10L  13/02 110 Z	2	0	5D045	G10L  13/02	588	¾Τ	Others
G10L  13/02 130 \	2	2	5D045	G10L  13/02	5	Ϥνħ	Characterized by treatment of voice output
G10L  13/02 130 A	2	0	5D045	G10L  13/02	93	ϲ椹	Controlling output numbers
G10L  13/02 130 B	2	0	5D045	G10L  13/02	177	Ͻ椹	Controlling output sequences
G10L  13/02 130 C	2	0	5D045	G10L  13/02	238	ʳ˽Ϥ벻椬¸ߤοȤδطθΡ㡥̤	Considering the existence of the output voice signals other than the synthetic voice and the relation between these signals, e.g. the volume control of voice
G10L  13/02 130 D	2	0	5D045	G10L  13/02	236	̤β׵᤬äȤν˴ؤΡ㡥եɥʸǤޤʸνλԤĤ	Technique relating to treatment when another voice output being required, e.g. fade in, interruption of previous sentence or wait for previous sentence to end
G10L  13/02 130 Z	2	0	5D045	G10L  13/02	799	¾Τ	Others
G10L  13/02 140 \	2	2	5D045	G10L  13/02	27	Ϥ줿ǡθ˴ؤΡ㡥̤ξղ	Relating to treating output voice data, e.g. add other information
G10L  13/02 141 \	3	3	5D045	G10L  13/02	0	ǡεϿ˴ؤ	Relating to recording of voice data
G10L  13/02 141 A	3	0	5D045	G10L  13/02	14	ǡΥХåå	Voice data backup
G10L  13/02 141 B	3	0	5D045	G10L  13/02	234	ŪѤΡ沽ħΣǣ̣	Using static memory ( having characteristic in coding G10L19/00 )
G10L  13/02 141 C	3	0	5D045	G10L  13/02	62	ɥåȥѥޤϥСѤƵϿ	Recording by using dot pattern, bar code or the like
G10L  13/02 141 D	3	0	5D045	G10L  13/02	85	̵ԤäƵϿΡ㡥ΨŪ˵Ͽ뤿Τ	Recording by silent elimination treating, e.g. for efficient recording
G10L  13/02 141 Z	3	0	5D045	G10L  13/02	54	¾Τ	Others
G10L  13/02 143 \	3	3	5D045	G10L  13/02	54	ϲǡɾ˴ؤ	Relating to evaluation of output voice data
G10L  13/02 144 \	3	3	5D045	G10L  13/02	1	ϲǡФ̤ξղä	Adding information according to output voice data
G10L  13/02 144 A	3	0	5D045	G10L  13/02	16		Copyright information
G10L  13/02 144 B	3	0	5D045	G10L  13/02	9	ϲǡεϿκݤ̤ξղä	Add information when recording output voiice data
G10L  13/02 144 Z	3	0	5D045	G10L  13/02	58	¾Τ	Others
G10L  13/027  \	2	2	5D045	G10L  13/027	397	ǰ鲻ؤι˴ŤǰμʥƥȤ鲻뤿Υѥ᡼ǣ̣ˡΣ	Concept to speech synthesisers; Generation of natural phrases from machine-based concepts (generation of parameters for speech synthesis out of text G10L 13/08) [2013.01]
G10L  13/033  \	2	2	5D045	G10L  13/033	60	Խ㡥βΣ	Voice editing, e.g. manipulating the voice of the synthesiser [2013.01]
G10L  13/033 101 \	3	3	5D045	G10L  13/033	0	ʹ䤹ΤΤ	for listenability
G10L  13/033 101 A	3	0	5D045	G10L  13/033	175	򲻤	Insertion of blank sound
G10L  13/033 101 B	3	0	5D045	G10L  13/033	18	©Ѥ	Insertion of rest sound
G10L  13/033 101 Z	3	0	5D045	G10L  13/033	79	¾Τ	Others
G10L  13/033 102 \	3	3	5D045	G10L  13/033	2	ϲФͿޤϥѥ᡼ħ	characterized by information and parameter given to output voice
G10L  13/033 102 A	3	0	5D045	G10L  13/033	145		Feelings
G10L  13/033 102 B	3	0	5D045	G10L  13/033	469		Music scale
G10L  13/033 102 Z	3	0	5D045	G10L  13/033	267	¾Τ	Others
G10L  13/04  \	2	2	5D045	G10L  13/04	2	ƥκ㡥ι¤ޤϥΣ	Details of speech synthesis systems, e.g. synthesiser structure or memory management [7,2013.01]
G10L  13/04  A	2	0	5D045	G10L  13/04	10	ŵŪʤѤ	Using non-electric means
G10L  13/04  F	2	0	5D045	G10L  13/04	138	֤ΰ۾˴ؤ	Relating to defect of voice synthesizer
G10L  13/04  Z	2	0	5D045	G10L  13/04	197	¾Τ	Others
G10L  13/047  \	3	3	5D045	G10L  13/047	1	ΥƥΣ	Architecture of speech synthesisers [2013.01]
G10L  13/047  A	3	0	5D045	G10L  13/047	506	ϩħΡ㡥ŸΤβϩ߷	characterised by circuits, e.g. power source management , memory management;circuit design thereof
G10L  13/047  B	3	0	5D045	G10L  13/047	50	֤Υϡǽ˴ŤƲԤ	Speech synthesis based on hardware ability of apparatus
G10L  13/047  C	3	0	5D045	G10L  13/047	104	ʬ˴ؤ	relating to decentralized processing
G10L  13/047  D	3	0	5D045	G10L  13/047	106	Ĥβʤʣβϼʤ֤ͭ˴ؤ	relating to apparatus having one voice producing mean and multiple voice output means
G10L  13/047  E	3	0	5D045	G10L  13/047	469	ͥåȥѤѤ	using network technology
G10L  13/047  Z	3	0	5D045	G10L  13/047	129	¾Τ	Others
G10L  13/06  \	1	1	5D045	G10L  13/06	3	ǻȤ벻ҡ絬§Σ	Elementary speech units used in speech synthesisers; Concatenation rules [7,2013.01]
G10L  13/06 100 \	2	2	5D045	G10L  13/06	9	ñ̲˴ؤ	Relating to generation of synthetic unitvoice
G10L  13/06 110 \	3	3	5D045	G10L  13/06	2	ȷ˴ؤ	Relating to waveform synthesis processing
G10L  13/06 110 A	3	0	5D045	G10L  13/06	116	ȷ򰵽̤ƵϿ	Recording by compressing waveform
G10L  13/06 110 Z	3	0	5D045	G10L  13/06	125	¾Τ	Others
G10L  13/06 120 \	3	3	5D045	G10L  13/06	0	ѥ᡼˴ؤ	Relating to parameter synthesis system
G10L  13/06 120 A	3	0	5D045	G10L  13/06	115	եޥȷ	Formant type synthesis system
G10L  13/06 120 B	3	0	5D045	G10L  13/06	16	ãӣ	CSM system
G10L  13/06 120 C	3	0	5D045	G10L  13/06	56	ȹ	Sine wave synthesis system
G10L  13/06 120 Z	3	0	5D045	G10L  13/06	438	¾Τ	Others
G10L  13/06 130 \	3	3	5D045	G10L  13/06	151	ȣͣͲѤ˴ؤ	Relating to HMM artificial-voice technology
G10L  13/06 140 \	3	3	5D045	G10L  13/06	112	ǣ̣ǣ̣ޤʤñ̲	Generation of synthetic unitvoice not being classified in G10L13/06, 110-G10L13/06, 130
G10L  13/06 200 \	2	2	5D045	G10L  13/06	304	Ѥ뼭˴ؤ	Relating to dictionary used for voice synthesis
G10L  13/06 210 \	3	3	5D045	G10L  13/06	2	Ѥޤ³ǡñ̤ħ	Characterized by unit of data stored or connected
G10L  13/06 210 A	3	0	5D045	G10L  13/06	109	ãַ	CV type
G10L  13/06 210 B	3	0	5D045	G10L  13/06	40	֣ãַޤϣã֣÷	VCV and CVC type
G10L  13/06 210 C	3	0	5D045	G10L  13/06	206	ʸϤޤʸñ	Sentences and clauses
G10L  13/06 210 Z	3	0	5D045	G10L  13/06	262	¾Τ	Others
G10L  13/06 220 \	3	3	5D045	G10L  13/06	0	Τͭε	Peculiar technology to storing medium
G10L  13/06 220 A	3	0	5D045	G10L  13/06	124	ưŪϿ	Dynamic recording
G10L  13/06 220 B	3	0	5D045	G10L  13/06	80	ŪϿ	Static recording
G10L  13/06 220 C	3	0	5D045	G10L  13/06	65	ưŪϿŪϿȹ礻	Combination of the dynamic record and the static record
G10L  13/06 220 Z	3	0	5D045	G10L  13/06	26	¾Τ	Others
G10L  13/06 230 \	3	3	5D045	G10L  13/06	2	ˡħ	Characterized by storing method
G10L  13/06 230 A	3	0	5D045	G10L  13/06	189	Ҥζ븵ħ	characterized by the source for providing the pieces
G10L  13/06 230 B	3	0	5D045	G10L  13/06	123	ΰͭѤ뤿Τ	for utilizing the memory area effectively
G10L  13/06 230 C	3	0	5D045	G10L  13/06	236	Ѥñ̤ħ	Characterized by unit of storing
G10L  13/06 230 Z	3	0	5D045	G10L  13/06	561	¾Τ	Others
G10L  13/06 240 \	3	3	5D045	G10L  13/06	0	ˡħ	Characterized by output method
G10L  13/06 240 A	3	0	5D045	G10L  13/06	51	ٱʤΤ	for cancelling the delay
G10L  13/06 240 Z	3	0	5D045	G10L  13/06	416	¾Τ	Others
G10L  13/07  \	2	2	5D045	G10L  13/07	0	絬§Σ	Concatenation rules [2013.01]
G10L  13/07  A	2	0	5D045	G10L  13/07	150	³ˡħ	characterized by connection method
G10L  13/07  B	2	1	5D045	G10L  13/07	377	³ȷħ	characterized by selection between connecting waveform
G10L  13/07  C	2	1	5D045	G10L  13/07	464	³ȷ֤ħΡ㡥ࡼ󥰤ޤ	characterized by operation between connecting waveform, e.g. smoothing, interpolation
G10L  13/07  Z	2	0	5D045	G10L  13/07	10	¾Τ	Others
G10L  13/08  \	1	1	5D045	G10L  13/08	26	ƥȤ鲻뤿ΡƥȤʬϡޤϥѥ᡼㡥ɽǤ鲻ǤؤѴΧޤ϶ޤϥȥ͡ηΣ	Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination [7,2013.01]
G10L  13/08 110 \	2	2	5D045	G10L  13/08	11	ʸϲ˴ؤ	Relating to sentence analysis part
G10L  13/08 110 A	2	0	5D045	G10L  13/08	339	Ϥħ	Characterized by language analysis
G10L  13/08 110 Z	2	0	5D045	G10L  13/08	182	¾ν	Other processes
G10L  13/08 120 \	2	2	5D045	G10L  13/08	34	§˴ؤ	Relating to speech synthesis rule part
G10L  13/08 121 \	3	3	5D045	G10L  13/08	85	˴ؤ	Relating to phoneme
G10L  13/08 122 \	4	4	5D045	G10L  13/08	594	ƤѹΡ㡥ʤɽˡѹޤϸФΤߤɤ߾夲ά줫ܺٸؤѹ	Changing content, e.g. expression method (dialect or the like.), reading out only summaries or heading, abbreviation to detailed word.
G10L  13/08 123 \	4	4	5D045	G10L  13/08	102	̤Ͽ˴ؤ	Relating to unregistered word
G10L  13/08 124 \	4	4	5D045	G10L  13/08	760	Ѳ뤿ξħΡ㡥ǧ̡𡤾ꡤޤϥޥϾ֤ˤѲ	Characterized by information intended to change contents, e.g. speech recognition result, feelings, place, situation, input state by mouse.
G10L  13/08 150 \	2	2	5D045	G10L  13/08	0	˴ؤ	Relating to speech synthesis part
G10L  13/08 150 A	2	0	5D045	G10L  13/08	114	ե륿ħ	Characterized by filter
G10L  13/08 150 B	2	0	5D045	G10L  13/08	161	ħ	Characterized by sound source generation part
G10L  13/08 150 Z	2	0	5D045	G10L  13/08	103	¾	Others
G10L  13/08 160 \	2	2	5D045	G10L  13/08	145	ϿԽȵ§Ȥ߹碌	Combination of recording and editing composition method and rule composition.
G10L  13/10  \	2	2	5D045	G10L  13/10	3	ƥȤƳФ줿Χ§Ĵޤϥȥ͡Σ	Prosody rules derived from text; Stress or intonation [2013.01]
G10L  13/10 110 \	3	3	5D045	G10L  13/10	71	Χ˴ؤ	relating to rhythm
G10L  13/10 111 \	4	4	5D045	G10L  13/10	3	ꤹѥ᡼ħ	characterized by parameter
G10L  13/10 111 A	4	0	5D045	G10L  13/10	456	ԥå	Pitch
G10L  13/10 111 B	4	0	5D045	G10L  13/10	323		Accent
G10L  13/10 111 C	4	0	5D045	G10L  13/10	391	ԥåѥ	Pitch pattern
G10L  13/10 111 D	4	0	5D045	G10L  13/10	206	ݡ	Pose
G10L  13/10 111 E	4	0	5D045	G10L  13/10	336	ѥ	Power
G10L  13/10 111 F	4	0	5D045	G10L  13/10	599	³	Duration
G10L  13/10 111 Z	4	0	5D045	G10L  13/10	206	¾Τ	Others
G10L  13/10 112 \	4	4	5D045	G10L  13/10	3	ȷѲ	Changing waveform
G10L  13/10 112 A	4	0	5D045	G10L  13/10	111	ʣȷ򤹤	Selecting plural waveforms
G10L  13/10 112 B	4	1	5D045	G10L  13/10	324	üԤڤؤ	Switching speaker
G10L  13/10 112 C	4	1	5D045	G10L  13/10	87	Ϳ봶ˤ򤹤	Selecting based on feelings
G10L  13/10 112 E	4	0	5D045	G10L  13/10	260	ƤȷѲ	Changing stored waveform
G10L  13/10 112 Z	4	0	5D045	G10L  13/10	50	¾Τ	Others
G10L  13/10 113 \	4	4	5D045	G10L  13/10	2	ʬϤޤˡħ	Characterized by analysis or setting method
G10L  13/10 113 A	4	0	5D045	G10L  13/10	34	̲Ѥ	Using first class of quantification
G10L  13/10 113 B	4	0	5D045	G10L  13/10	299	Ϥ˴ؤ	Relating to language analysis
G10L  13/10 113 C	4	0	5D045	G10L  13/10	239	ղäƤ뼱̾Ѥ	Using added identification information
G10L  13/10 113 Z	4	0	5D045	G10L  13/10	492	¾Τ	Others
G10L  13/10 114 \	4	4	5D045	G10L  13/10	931	Ѳ뤿ξħΡ㡥ǧ̡𡤾ꡤޤϥޥϾ֤ˤѲ	Characterized by information for changing, e.g. speech recognition result, feelings, place, situation, input state by mouse
G10L  15/00  \	0	0	5D015	G10L  15/00	31	ǧʣǣ̣ͥˡΣ	Speech recognition () [7,2013.01]
G10L  15/00 153 \	1	1	5D015	G10L  15/00	2	ǧޤϼ̤Ԥ	using speech recognition or verification
G10L  15/00 200 \	2	2	5D015	G10L  15/00	2	ǧʤǤȤ	Devices using speech recognition means as components
G10L  15/00 200 A	2	0	5D015	G10L  15/00	3128	òޤ̿Ѥ֡㡥ä饤󥿡ͥå֤ѤüۥȤǲǧԤ	Devices utilizing telephone circuits or communication circuits, e.g. a device to recognize voice in the terminal host by utilizing the internet network from a cellular phones
G10L  15/00 200 B	2	0	5D015	G10L  15/00	953	ǧѤƸ㡥ʸ󡤤ϤΡʤץޤϲץ饤	Language information by using the voice recognition, e.g. the input of character strings, i.e., the voice word processor or the voice typewriter
G10L  15/00 200 P	2	0	5D015	G10L  15/00	618	׻ޤϥѥ	Calculators or personal computers
G10L  15/00 200 T	2	1	5D015	G10L  15/00	588	֤ؤϤȤƲǧѤ	Speech recognition used to enter retrieval device
G10L  15/00 200 C	2	0	5D015	G10L  15/00	850	㡥۸֤ޤϰʪ֤֡㡥㳲Ԥβ	Translating machine, e.g. the translation between different languages or between different lives; the conversation assisting unit e.g. the conversation assisting for handicapped persons
G10L  15/00 200 D	2	0	5D015	G10L  15/00	102	ȯη¬	measuring frequency of voice generation
G10L  15/00 200 E	2	0	5D015	G10L  15/00	410	ȯ֡㡥ޤϼȯηǧʤǤȤ붵	Voice training unit, e.g. the voice training in foreign language or in mother tongue; the training tool constituted by the voice recognition means as an element
G10L  15/00 200 F	2	0	5D015	G10L  15/00	436	⡼ȥȥ	Voice-activated remote control devices
G10L  15/00 200 G	2	0	5D015	G10L  15/00	1827	ޤϲ㡥ԣ֣֡ԣҤޤϣãġʣǣ̣ͥ	Video or sound equipment, e.g. TV, VTR or CD (G10L15/00, 200U takes precedence)
G10L  15/00 200 U	2	0	5D015	G10L  15/00	403	ŻҲĥƥ	Electronic meeting system
G10L  15/00 200 H	2	0	5D015	G10L  15/00	878	ޤϤ	Games or toys
G10L  15/00 200 J	2	0	5D015	G10L  15/00	1242	ưΡ㡥ư֡졼ޤϥ١	Movable bodies, e.g. automobiles, cranes or elevators
G10L  15/00 200 Q	2	0	5D015	G10L  15/00	1057	ʥӥ󥷥ƥ	Navigation systems
G10L  15/00 200 K	2	0	5D015	G10L  15/00	147	ư䵡ޤϥåǥڥ	Vending machines or cash dispensers
G10L  15/00 200 L	2	0	5D015	G10L  15/00	436	֤֡ޤϰ	Testing machines, test equipment, metering apparatus or devices for medical use
G10L  15/00 200 R	2	0	5D015	G10L  15/00	65	ץ	Plant control
G10L  15/00 200 M	2	0	5D015	G10L  15/00	68		Time-pieces
G10L  15/00 200 N	2	0	5D015	G10L  15/00	379	ʤʣǣ̣Ǥͥ	controlling electronic appliance (G10L15/00, 200G takes precedence)
G10L  15/00 200 S	2	0	5D015	G10L  15/00	328	ޤϥƥƥ	Keys, entry control or security systems
G10L  15/00 200 Z	2	0	5D015	G10L  15/00	1516	¾Τ	Others
G10L  15/01  \	1	1	5D015	G10L  15/01	30	ǧƥɾΣ	Assessment or evaluation of speech recognition systems [2013.01]
G10L  15/01 200 \	2	2	5D015	G10L  15/01	141	㡥ǧ֡ǥޤϸǥ뤬٤ǧԤ뤫λ	Test, e.g. whether speech recognition means, acoustic model or language model can  recognize accurately
G10L  15/02  \	1	1	5D015	G10L  15/02	5	ǧΤħСǧñ̤Σ	Feature extraction for speech recognition; Selection of recognition unit [7]
G10L  15/02 153 \	2	2	5D015	G10L  15/02	1	ħѥ᡼	Extraction of feature parameters
G10L  15/02 200 \	3	3	5D015	G10L  15/02	5	ħѥ᡼ФΤΰ̵	General techniques for extraction of feature parameters
G10L  15/02 200 A	3	0	5D015	G10L  15/02	158	ħΰ̡ԶѰ쥵ץ󥰡㡥ޤӰˤäФħѥ᡼οѤȤ	Compression of the characteristics; the ununiform sampling, e.g. enabling the number of the characteristic parameters extracted by time or band to be variable
G10L  15/02 200 B	3	0	5D015	G10L  15/02	272	٥ȥ̻Ҳ	Vector quantisation
G10L  15/02 200 D	3	0	5D015	G10L  15/02	143	ͭޤ̵֤θФޤ̤Ԥ	detecting or discriminating between voiced and unvoiced parts
G10L  15/02 200 Z	3	0	5D015	G10L  15/02	129	¾Τ	Others
G10L  15/02 300 \	3	3	5D015	G10L  15/02	1	Фħѥ᡼ħ	characterised by feature parameters to be extracted
G10L  15/02 300 A	3	0	5D015	G10L  15/02	163	ưŪħС㡥Ѳ	Extraction of dynamic features, e.g. amount of time variation
G10L  15/02 300 B	3	0	5D015	G10L  15/02	231	ڥȥޤϥեޥȾ	Extraction of spectrum envelope information or formant information
G10L  15/02 300 C	3	0	5D015	G10L  15/02	198	ؾ	Extraction of correlation information
G10L  15/02 300 D	3	0	5D015	G10L  15/02	419	ȯİ赡ϵѤħѥ᡼С㡥륹ޤĴ	Extraction of feature parameters using simulated vocalising or listening mechanisms, e.g. mel scale or the place of articulation
G10L  15/02 300 E	3	0	5D015	G10L  15/02	102	򺵾	Extraction of information of zero crossing
G10L  15/02 300 F	3	0	5D015	G10L  15/02	175	ͽ¬ѤѤФħѥ᡼	Feature parameters to be extracted with predictive techniques
G10L  15/02 300 G	3	0	5D015	G10L  15/02	251	ľؿѤФħѥ᡼	Feature parameters to be extracted with orthogonal functions
G10L  15/02 300 H	3	0	5D015	G10L  15/02	20	ŵŪѤѤФħѥ᡼	Feature parameters to be extracted with non-electrical techniques
G10L  15/02 300 J	3	0	5D015	G10L  15/02	766	ȿΰˤǣ̣ǣ̣Ȱʳħѥ᡼С㡥	Extraction of feature parameters other than G10L15/02, 300A-G10L15/02, 300H in the frequency domain, e.g. voiceprint
G10L  15/02 300 K	3	0	5D015	G10L  15/02	619	ΰˤǣ̣ǣ̣Ȱʳħѥ᡼С㡥ԥåȯ÷³Ĺޤϥѥ	Extraction of feature parameters other than G10L15/02, 300A-G10L15/02, 300H in the time domain, e.g. pitch, utterance continuation length or power.
G10L  15/02 300 Z	3	0	5D015	G10L  15/02	193	¾Τ	Others
G10L  15/04  \	1	1	5D015	G10L  15/04	2	ơ󡨸維СΣ	Segmentation; Word boundary detection [7,2013.01]
G10L  15/04 153 \	2	2	5D015	G10L  15/04	10	Ȳħͭ	characterised by segmentation
G10L  15/04 200 \	3	3	5D015	G10L  15/04	452	ơ󡨸ڤ측	Segmentation or word limit detection
G10L  15/04 300 \	3	3	5D015	G10L  15/04	11	֤ηꡨλüü	Decision of voice interval or detection of voice beginning and end
G10L  15/04 300 A	3	0	5D015	G10L  15/04	815	ΥѥѤΡ㡥ΥѥͤӤ	using the voice power, e.g. the comparison of the voice power with the threshold value
G10L  15/04 300 B	3	0	5D015	G10L  15/04	450	Υѥʳβħ㡥򺵿Υѥκʬޤϼȿħ̡Ѥ	Voice characteristics other than the voice power, e.g. the use of the zero crossing number, the difference in the voice power or the amount of the frequency characteristics
G10L  15/04 300 C	3	0	5D015	G10L  15/04	290	ϲ椫Фħ̤ɸѥ㡥̵ͭѥޤϻѥ󡤤ȤӤˤ	The amount of characteristic and the standard pattern extracted from the input voice signals, e.g. the comparison with the voice/silent pattern or the noise pattern
G10L  15/04 300 D	3	0	5D015	G10L  15/04	106	ʣβָͿ	giving several voice intervals
G10L  15/04 300 Z	3	0	5D015	G10L  15/04	576	¾Τ	Others
G10L  15/05  \	2	2	5D015	G10L  15/05	4	維СΣ	Word boundary detection [2013.01]
G10L  15/06  \	1	1	5D015	G10L  15/06	6	ɸѥκǧƥγؽ㡥üŬʣǣ̣ͥˡΣ	Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker&apos;s voice () [7,2013.01]
G10L  15/06 153 \	2	2	5D015	G10L  15/06	1	ɸѥ˴ؤ	in respect of reference templates
G10L  15/06 200 \	3	3	5D015	G10L  15/06	0	ɸѥϿޤɸѥεΤ˴ؤ	of registration process or storage medium of reference templates
G10L  15/06 200 A	3	0	5D015	G10L  15/06	247	ɸѥ򵭲꼫ΤħΡ㡥곰ǽʥѥåɣåɡɤޤϥǥѤΡ֤Ȥδ֤ǥѥΤ꤬Ǥ	characterized by the memory per se for storing the standard pattern, e.g. the utilization of detachable memory pack, IC card, magnetic card or disk; the exchange of patterns with the external storage unit
G10L  15/06 200 B	3	0	5D015	G10L  15/06	324	Ͽ㡥ɸѥκݤȯȯ٤Ǥ뤫̤ޤȯ®٤Ϥɤ٤Ǥ٤򤢤餫󼨤ΡϿƤγǧ㡥ȯϿȯΤǤ뤫ǧΤޤϿѤߤβΤǤ뤫ǧ	Assistance to the registration process, e.g. advance provision of what kind of voice should be uttered when the standard pattern is created, and how we should adjust the volume of voice or the speed of speech?; Confirmation of the contents to be registered, e.g. the confirmation of the correctness of the speech by reproducing the uttered voice after the utterance and before the registration
G10L  15/06 200 Z	3	0	5D015	G10L  15/06	77	¾Τ	Others
G10L  15/06 300 \	3	3	5D015	G10L  15/06	2	ӳؽ	Creation or training process
G10L  15/06 300 C	3	0	5D015	G10L  15/06	631	ɸѥκħ	characterised by creation of reference templates
G10L  15/06 300 D	3	0	5D015	G10L  15/06	278	ɸѥؽˤѷ	Deformation of reference templates through learning
G10L  15/06 300 E	3	0	5D015	G10L  15/06	337	ѥ㡥֤ˤۤפȡ֤ˤäݤסϿΡޤѥϿӽ	Registration of analogous pattern, e.g. "Nihon" and "Nippon"; Exclusion of analogous pattern from registration
G10L  15/06 300 G	3	0	5D015	G10L  15/06	197	ɸѥʿѽԤ	averaging process of reference templates
G10L  15/06 300 H	3	0	5D015	G10L  15/06	223	ɸѥ֤Ԥ	rewriting reference templates
G10L  15/06 300 J	3	0	5D015	G10L  15/06	497	ץѥΤޤɬץѥɲä	removing unwanted templates or addition of desired templates
G10L  15/06 300 M	3	0	5D015	G10L  15/06	163	ɸѥϿޤϳؽʣΥ⡼ɤǹԤ	Registration of reference templates or learninig in multiple modes
G10L  15/06 300 Y	3	0	5D015	G10L  15/06	550	ɸѥκޤϳؽѤ벻ǡħ	Characterized by creation of reference templates or selection of data for training
G10L  15/06 300 Z	3	0	5D015	G10L  15/06	285	¾Τ	Others
G10L  15/06 400 \	3	3	5D015	G10L  15/06	0	ɸѥι¤ޤϼ˴ؤ	of construction or kinds of reference templates
G10L  15/06 400 U	3	0	5D015	G10L  15/06	100	ɥ֥åͭΡؽѲǡΥ饹	With code book; clustering of the voice data for learning
G10L  15/06 400 V	3	0	5D015	G10L  15/06	743	ɸѥʣͭ	having several pairs of reference templates
G10L  15/06 400 W	3	0	5D015	G10L  15/06	237	ع¤ɸѥ	Standard pattern of the layered structure
G10L  15/06 400 Z	3	0	5D015	G10L  15/06	150	¾Τ	Others
G10L  15/06 500 \	3	3	5D015	G10L  15/06	0	Ŭʬ˴ؤ	of application fields
G10L  15/06 500 K	3	0	5D015	G10L  15/06	68	ȯ®ưۼΤΤ	for absorbing vocalisation speed variation
G10L  15/06 500 L	3	0	5D015	G10L  15/06	347	ɸѥޤϳؽк㡥꡼ĶѤɸѥȳƼﻨɸѥȤƻĶѤɸѥΡʣǣ̣ͥ	Pre-treatment during the creation of standard pattern or during the learning; countermeasures against noise, e.g. the creation of the standard pattern under the noisy environment by synthesizing the standard pattern under the clean environment with the standard pattern under various noise (G10L15/065A takes precedence.)
G10L  15/06 500 N	3	0	5D015	G10L  15/06	177	üǧΤΤ	for unspecified speaker&apos;s recognition
G10L  15/06 500 P	3	0	5D015	G10L  15/06	251	üǧΤΤ	for speaker&apos;s recognition
G10L  15/06 500 Q	3	0	5D015	G10L  15/06	37	Ϣ³ǧΤΤ	for continuous speech recognition
G10L  15/06 500 Z	3	0	5D015	G10L  15/06	71	¾Τ	Others
G10L  15/065  \	2	2	5D015	G10L  15/065	9	ŬΣ	Adaptation [2013.01]
G10L  15/065  A	2	0	5D015	G10L  15/065	301	Ķ㡥ŬѤŬ	adaptive process for adaptation in environment, e.g. noise
G10L  15/065  Z	2	0	5D015	G10L  15/065	224	¾Τ	Others
G10L  15/07  \	3	3	5D015	G10L  15/07	410	üԤФΡΣ	to the speaker [2013.01]
G10L  15/08  \	1	1	5D015	G10L  15/08	4	μ̤ޤõΣ	Speech classification or search [7]
G10L  15/08 153 \	2	2	5D015	G10L  15/08	6	õˡħͭΡʣǣ̣ͥ	characterised by search techniques (G10L15/10-15/18 take precedence)
G10L  15/08 200 \	3	3	5D015	G10L  15/08	0	õˡ	Hypothesis search techniques
G10L  15/08 200 J	3	0	5D015	G10L  15/08	118	ӡॵ	Beam search
G10L  15/08 200 Z	3	0	5D015	G10L  15/08	94	¾Τ	Others
G10L  15/08 300 \	3	3	5D015	G10L  15/08	0	ȹߤΡȹ̤ꥸȤޤϴѤ	Stoppage of the verification; rejection or abolition of the verified results
G10L  15/08 300 B	3	0	5D015	G10L  15/08	288	ꥸȥ٥˴ؤΡꥸȥ٥뤬ѤΤ	Regarding the setting of the reject-level; variable in the reject-level
G10L  15/08 300 Z	3	0	5D015	G10L  15/08	434	¾Τ	Others
G10L  15/10  \	2	2	5D015	G10L  15/10	13	̤βɸѥȤεΥޤĤߤѤΡΣ	using distance or distortion measures between unknown speech and reference templates [7]
G10L  15/10 153 \	3	3	5D015	G10L  15/10	9	ɸѥȤεΥ׻ˤޤŬʬħͭ	characterised by processing while calculating distance to reference templates or application fields
G10L  15/10 200 \	4	4	5D015	G10L  15/10	0	ȹ֤ޤϾȹ֤˴ؤ	in respect of checking interval or position
G10L  15/10 200 A	4	0	5D015	G10L  15/10	76	ȹ硤㡥ñΤ˿̤ȲꤷϥѥɸѥȤȹ礹	Linear verification, e.g. the item characterized by the verification of the input pattern with the standard pattern under the assumption that the whole words can be extended/contracted linearly
G10L  15/10 200 B	4	0	5D015	G10L  15/10	89	ȹ硤㡥ñλּο̤˹ԤȲꤷϥѥɸѥȹ礹Ρʣǣ̣ǣ̣ӣǣ̣ʤͥ	Non-linear verification, e.g. the item characterized by the verification of the input pattern with the standard pattern under the assumption that the extension/contraction of the words on the time axis is carried out non-linearly (G10L15/12 through G10L15/16 and G10L16/10, 300J take precedence.)
G10L  15/10 200 C	4	0	5D015	G10L  15/10	364	ȹ֤ޤϾȹ֤ꡨ̵ΰֹ碌	Identification of the verifying segment or the verifying position; positioning of the silent portion
G10L  15/10 200 W	4	1	5D015	G10L  15/10	2081	ɥݥåƥ󥰡ʤϤ줿оݤȤʤñ򸡽Ф뵻Ѥ˴ؤ	Regarding the word spotting, i.e, the technology to detect the targeted word in the input voice signals
G10L  15/10 200 Z	4	0	5D015	G10L  15/10	35	¾Τ	Others
G10L  15/10 300 \	4	4	5D015	G10L  15/10	0	Ѥ٤ޤϵΥ˴ؤ	of degree of similarity or distance to be used
G10L  15/10 300 F	4	0	5D015	G10L  15/10	326	ΨŪ١㡥ΨޤŪΥ١Ѥ	Use of probability measurement, e.g. follow-up probability or statistical measurement of process
G10L  15/10 300 G	4	0	5D015	G10L  15/10	538	٤ޤϵΥ黻˽Ťդ򤹤	weighting during calculating degree of similarity or distance
G10L  15/10 300 H	4	0	5D015	G10L  15/10	77	ե塼ޥȥåѤ٤ޤϵΥ黻Ԥ	characterized by the calculation of the degree of the resemblance or the distance by using the confusion matrix
G10L  15/10 300 J	4	0	5D015	G10L  15/10	82	եޤϥѤ٤ޤϵΥ黻Ԥ	characterized by calculation of the degree of resemblance or the distance by using the fuzzy theory or the chaos theory
G10L  15/10 300 Z	4	0	5D015	G10L  15/10	515	¾Τ	Others
G10L  15/10 400 \	4	4	5D015	G10L  15/10	0	Ŭʬ˴ؤ	of application fields
G10L  15/10 400 J	4	0	5D015	G10L  15/10	117	üǧ	Unspecified speaker&apos;s recognition
G10L  15/10 400 K	4	1	5D015	G10L  15/10	438	üԾȹޤüǧȤΡʤ餫Ჿ餫ˡüԤïǤ뤫Ƚ̤üԤбɸѥ򤷤Ʋǧ뤳ȤˤäƷŪüǧ	The subject matter that presupposes the speaker verification or speaker recognition. Namely, the unspecified speaker recognition is conducted as the result of the discrimination of the speaker in advance by using a certain method, and the voice recognition by selecting the standard pattern corresponding to that speaker.
G10L  15/10 400 M	4	0	5D015	G10L  15/10	172	Ϣ³ǧ	Continuous speech recognition
G10L  15/10 400 R	4	0	5D015	G10L  15/10	324	겻ǧ㡥Ҳ첻ޤɡ	Recognition of specific sound, e.g. consonant, vowel or nasal
G10L  15/10 400 Z	4	0	5D015	G10L  15/10	29	¾Τ	Others
G10L  15/10 500 \	4	4	5D015	G10L  15/10	4	ȯòȯưʳΤΤȽꤹ	determining other than contents of utterance from speech utterance
G10L  15/10 500 N	4	0	5D015	G10L  15/10	767	θСʲʬϤˤäƸФΣǣ̣	detecting emotion (detecting by speech analysis, see G10L25/63)
G10L  15/10 500 T	4	0	5D015	G10L  15/10	1172	̣ޤС㡥ǧ̩ܤ˴Ϣ󵻽	understanding meaning or extraction of the gist, e.g. summarising techniques intimately associated with speech recognition processes
G10L  15/10 500 Z	4	0	5D015	G10L  15/10	1979	¾Τ	Others
G10L  15/12  \	2	2	5D015	G10L  15/12	0	ưŪײˡѤΡ㡥ưŪֿ̡ΣģԣסϡΣ	using dynamic programming techniques, e.g. dynamic time warping [DTW] [7]
G10L  15/12  A	2	0	5D015	G10L  15/12	147	Ϣ³ǧ	Continuous speech recognition
G10L  15/12  C	2	0	5D015	G10L  15/12	60	Ťդȹ礹	weighting and collating
G10L  15/12  D	2	0	5D015	G10L  15/12	121	¡¤ޤü	Limit in window or in tilting or particular recurrence formula
G10L  15/12  E	2	0	5D015	G10L  15/12	28	̤줿ѥȤξȹ	collating with compressed pattern
G10L  15/12  Z	2	0	5D015	G10L  15/12	276	¾Τ	Others
G10L  15/14  \	2	2	5D015	G10L  15/14	5	ŪǥѤΡ㡥ޥ륳եǥΣȣͣ͡ϡʣǣ̣ͥˡΣ	using statistical models, e.g. Hidden Markov Models [HMM] (G10L 15/18&nbsp;takes precedence) [7]
G10L  15/14 153 \	3	3	5D015	G10L  15/14	32	ħ̤ѤŪǥ	with feature quantity of speech
G10L  15/14 200 \	4	4	5D015	G10L  15/14	392	ޥ륳եǥΣȣͣ͡	Hidden Markov Models (HMM)
G10L  15/14 200 A	4	0	5D015	G10L  15/14	200	Ψ黻ħ	characterised by probability computing
G10L  15/14 200 B	4	0	5D015	G10L  15/14	115	ӥӡΣ֣ϥ르ꥺѤ	using Viterbi algorithm
G10L  15/14 200 C	4	0	5D015	G10L  15/14	163	Ψ̩ʬۤΤ	Mixed probability density distribution
G10L  15/14 200 D	4	0	5D015	G10L  15/14	23	ưŪײˡФƸߤŬѲǽʵѤͭ	having applicable techniques one another against dynamic programming
G10L  15/14 200 Z	4	0	5D015	G10L  15/14	482	¾Τ	Others
G10L  15/16  \	2	2	5D015	G10L  15/16	926	˥塼롦ͥåȥѤΡΣ	using artificial neural networks [7]
G10L  15/18  \	2	2	5D015	G10L  15/18	24	ǥѤΡΣ	using natural language modelling [7,2013.01]
G10L  15/18 300 \	3	3	5D015	G10L  15/18	1	ñ̤ħ	characterised by processing unit
G10L  15/18 300 G	3	0	5D015	G10L  15/18	477	ñ졤ʸᡤʾĹñ̤ǽ	Word, clause or unit of which length is longer to be processed
G10L  15/18 300 H	3	0	5D015	G10L  15/18	380	֥ñ̡㡥ᡤǤޤϲǽ	Subword unit, e.g. syllable, phoneme or phonological features, to be processed
G10L  15/18 300 Z	3	0	5D015	G10L  15/18	70	¾Τ	Others
G10L  15/18 400 \	3	3	5D015	G10L  15/18	284	˱ʣΥǥڤ괹	switching plural models in consequence of circumstances
G10L  15/183  \	3	3	5D015	G10L  15/183	32	ʸ̮¸ѤΡ㡥ǥΣ	using context dependencies, e.g. language models [2013.01]
G10L  15/183 200 \	4	4	5D015	G10L  15/183	1	ʸɽ˴ؤ	relating to syntax information representation
G10L  15/183 200 F	4	0	5D015	G10L  15/183	162	ڹ¤	Tree structure
G10L  15/183 200 K	4	0	5D015	G10L  15/183	91		Co-occurrence information
G10L  15/183 200 Z	4	0	5D015	G10L  15/183	433	¾㡥Ϣ˴ؤ	Others, specially in respect of chaining tendency
G10L  15/187  \	4	4	5D015	G10L  15/187	20	ǥƥȡ㡥ȯ§ˡޤϲǣݣΣ	Phonemic context, e.g. pronunciation rules, phonotactical constraints or&nbsp;phoneme n-grams [2013.01]
G10L  15/19  \	4	4	5D015	G10L  15/19	19	ʸˡŪƥȡ㡥絬§˴ŤǧۣáΣ	Grammatical context, e.g. disambiguation of recognition hypotheses based on word sequence rules [2013.01]
G10L  15/193  \	5	5	5D015	G10L  15/193	14	ʸˡ㡥ͭ¾֥ȥޥȥʸ̮ͳʸˡޤñͥåȥΣ	Formal grammars, e.g. finite state automata, context free grammars or word networks [2013.01]
G10L  15/193 100 \	6	6	5D015	G10L  15/193	224	ȥޥȥ󡤣ȣͣͤޤʸˡ	Automaton, HMM regular grammar
G10L  15/193 200 \	6	6	5D015	G10L  15/193	202	ʸ̮ͳʸˡ	Context free grammar
G10L  15/197  \	5	5	5D015	G10L  15/197	428	ΨŪʸˡ㡥ñݣΣ	Probabilistic grammars, e.g. word n-grams [2013.01]
G10L  15/20  \	1	1	5D015	G10L  15/20	3	ʴĶäŬǧѡ㡥ޤϥȤΤ벻ʣǣ̣ͥˡΣ	Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise or of stress induced speech (G10L 21/02&nbsp;takes precedence) [7]
G10L  15/20 153 \	2	2	5D015	G10L  15/20	8	ѲŬ뵻Ѥħͭ	characterised by techniques adapted for speech variation
G10L  15/20 200 \	3	3	5D015	G10L  15/20	0	ǧ˴ؤ	in respect of recognition process
G10L  15/20 200 Q	3	0	5D015	G10L  15/20	210	ǧ׸ޤϻɸѥѤΡ١ǥѤ	using a word of unnecessary recognition or reference templates of noise;  using garbage model
G10L  15/20 200 Z	3	0	5D015	G10L  15/20	312	¾Τ	Others
G10L  15/20 300 \	3	3	5D015	G10L  15/20	7	˴ؤ	in respect of preprocessing
G10L  15/20 353 \	4	4	5D015	G10L  15/20	585	ǧ˹Ԥħͭ	characterised by processing prior to recognition process
G10L  15/20 360 \	5	5	5D015	G10L  15/20	0		Speech signal normalisation
G10L  15/20 360 B	5	0	5D015	G10L  15/20	219	㡥ư경ޤϾ	Amplitude normalization e.g. the process to keep the amplitude variation to be constant or to reduce the amplitude variation
G10L  15/20 360 Z	5	0	5D015	G10L  15/20	308	¾Τ	Others
G10L  15/20 370 \	5	5	5D015	G10L  15/20	2	ʬ	Unnecessary component reduction
G10L  15/20 370 D	5	0	5D015	G10L  15/20	953		Noise reduction
G10L  15/20 370 E	5	0	5D015	G10L  15/20	585	İʾΥޥۥѤΡ㡥ѥޥۥȻѥޥۥ	Utilization of two or more microphones, e.g. a microphone for voice input and a microphone for noise input
G10L  15/20 370 F	5	0	5D015	G10L  15/20	212	ŬޤŬե륿Ѥ	using adaptive signal processing or adaptive filter
G10L  15/20 370 Z	5	0	5D015	G10L  15/20	317	¾Τ	Others
G10L  15/20 380 \	5	5	5D015	G10L  15/20	99	ʬĴ	enhancing speech parts
G10L  15/22  \	1	1	5D015	G10L  15/22	6	ǧμ硤㡥ޥ󡦥ޥáΣ	Procedures used during a speech recognition process, e.g. man-machine dialog [7]
G10L  15/22 153 \	2	2	5D015	G10L  15/22	5	ǧμħͭ	characterised by control of procedures of speech recognition
G10L  15/22 200 \	3	3	5D015	G10L  15/22	0	ǧ˴ؤ	in respect of recognition process
G10L  15/22 200 H	3	0	5D015	G10L  15/22	1226	ǧȯޤǧΰ⡤㡥ǧȯߥ󥰤ޤȯ٤ñ	Support for utterance of recognized voice or guidance for recognition procedures, e.g. the provision of the utterance timing during the voice recognition or the word that should be uttered
G10L  15/22 200 V	3	0	5D015	G10L  15/22	709	ǧоݤѹޤ¤Ρ㡥üԡޤϥƥ˱ǧоݸä¤ΡȹѤ벻ǥޤϸǥ¤	Alteration or restriction of the target of recognition, e.g. the restriction of the vocabrary targeted for recognition depending on the speaker, topic or category; the restriction of the acoustic model or the language model that are used for the reference
G10L  15/22 200 Z	3	0	5D015	G10L  15/22	79	¾Τ	Others
G10L  15/22 300 \	3	3	5D015	G10L  15/22	11	ý˴ؤΡǧ̩ܤ˴Ϣý	in respect of speech interactive process; intimately associated with speech recognition process
G10L  15/22 300 U	3	0	5D015	G10L  15/22	862	åǥѤ	Process with interactive models
G10L  15/22 300 Z	3	0	5D015	G10L  15/22	1675	¾Τ	Others
G10L  15/22 400 \	3	3	5D015	G10L  15/22	13	ǧ̤θ˴ؤ	in respect of post processing of recognition results
G10L  15/22 453 \	4	4	5D015	G10L  15/22	607	ǧθ˹Ԥħͭ	characterised by processing after recognition process
G10L  15/22 460 \	5	5	5D015	G10L  15/22	31	ǧ̤γǧޤɽ	validating or indicating recognition results
G10L  15/22 460 D	5	0	5D015	G10L  15/22	605	ޤϲˤ	by speech or sound
G10L  15/22 460 Z	5	0	5D015	G10L  15/22	1817	¾Τ	Others
G10L  15/22 470 \	5	5	5D015	G10L  15/22	3	ǧ̤	Correction for recognition results
G10L  15/22 470 F	5	0	5D015	G10L  15/22	249	ǧѤΡ㡥ǧΤ˸ǧȽꤵ줿Τϸ䤫	Utilization of the erroneous recognition trend, e.g. the exclusion of the recognition candidate that is previously judged as the erroneous recognition from the candidates
G10L  15/22 470 Z	5	0	5D015	G10L  15/22	907	¾Τ	Others
G10L  15/24  \	1	1	5D015	G10L  15/24	2	ʳħѤ벻ǧΣ	Speech recognition using non-acoustical features [7,2013.01]
G10L  15/24  Q	1	0	5D015	G10L  15/24	368	ǧʳǧʤޤϽѤ	Recognition means or processes other than speech recognition
G10L  15/24  R	1	0	5D015	G10L  15/24	173	ܡɡåޤϥܥ	keyboards, switches, or buttons
G10L  15/24  S	1	0	5D015	G10L  15/24	80	ȯƤθѤΡ㡥֤礦ȤΤ礦פȯֵפǧ̤ȤƽϤ	Utilization of the linguistic information in the utterance contents, e.g. the recognition and output of "Kyo" in the uttered sentence "Kyoto-no-kyo (Kyoto of today)
G10L  15/24  Z	1	0	5D015	G10L  15/24	382	¾㡥ǧʳμʤޤϽѤ	Others, specially using means or processes other than speech recognition
G10L  15/25  \	2	2	5D015	G10L  15/25	147	ΰ֡αưޤϴʬϤѤΡΣ	using position of the lips, movement of the lips or face analysis [2013.01]
G10L  15/26  \	1	1	5D015	G10L  15/26	35	ƥȤѴ륷ƥʣǣ̣ͥˡΣ	Speech to text systems (G10L 15/08 takes precedence) [7]
G10L  15/28  \	1	1	5D015	G10L  15/28	6	ǧƥι¤κΣ	Constructional details of speech recognition systems [7,2013.01]
G10L  15/28 153 \	2	2	5D015	G10L  15/28	2	ǧƥι¤ħͭ	characterised by structure of speech recognition systems
G10L  15/28 200 \	3	3	5D015	G10L  15/28	246	ǧ֤üʹޤϻ	Special structure, control or testing of speech recognition apparatus
G10L  15/28 230 \	4	4	5D015	G10L  15/28	3	ǧ֤ղŪǽ	Additional functions of speech recognition apparatus
G10L  15/28 230 J	4	0	5D015	G10L  15/28	392	ˡޤϥ⡼ɤ	Control or mode switch
G10L  15/28 230 K	4	0	5D015	G10L  15/28	1238	ǧγϡߡƳޤ϶ػߡ㡥ܥ󲡲Τǧоݶ֤Ȥ	Interruption, resumption or prohibition of the voice recognition, e.g. the assignment of only the period of button pressing as the interval targeted for the recognition
G10L  15/28 230 Z	4	0	5D015	G10L  15/28	156	¾Τ	Others
G10L  15/28 300 \	3	3	5D015	G10L  15/28	5	ǧüʽ	Special processing of speech recognition
G10L  15/28 353 \	4	4	5D015	G10L  15/28	36	ȹήħͭ	characterised by flow of collation process
G10L  15/28 400 \	3	3	5D015	G10L  15/28	1148	μʤħΡ㡥üޥۥ󡨥ޥۥ󥢥졼ꡨƳ	characterized by the voice detecting means, e.g. the special microphone; microphone array; detection of the sound direction; bone conduction
G10L  15/28 500 \	3	3	5D015	G10L  15/28	809	ǧ̤С㡥ǧ̤Хߥ󥰤椹Τޤǧ̤Ϥݤǧ̤ơ֥Ѵ	Transmission of the recognized results, e.g. the item to control the transmission timing of the recognized result or the item to convert the recognized result by using a table in case the recognized result is output
G10L  15/30  \	2	2	5D015	G10L  15/30	825	ʬǧ㡥饤ȡХƥˤΡäޤϥͥåȥץꥱΤΤΡΣ	Distributed recognition, e.g. in client-server systems, for mobile phones or network applications [2013.01]
G10L  15/32  \	2	2	5D015	G10L  15/32	4	缡ޤ˻Ѥʣǧ֡Ȥ߹碌륷ƥࡤ㡥ɼƥΣ	Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems [2013.01]
G10L  15/32 200 \	3	3	5D015	G10L  15/32	0	ʣٷ׻˹Ԥ	processing plural similarity calculations in parallel
G10L  15/32 200 A	3	0	5D015	G10L  15/32	96	¾Ȱۤʤɸѥ㡥Ѥȹ	Collation using different reference templates, e.g. syllable numbers
G10L  15/32 200 B	3	0	5D015	G10L  15/32	43	¾Ȱۤʤ륢르ꥺѤȹ	Collation using different algorithm
G10L  15/32 200 C	3	0	5D015	G10L  15/32	66	¾Ȱۤʤħ̤Ѥȹ	Collation using different feature quantities
G10L  15/32 200 Z	3	0	5D015	G10L  15/32	107	¾Τ	Others
G10L  15/32 210 \	3	3	5D015	G10L  15/32	3	ͽ򡤺ƾȹ	Preselection or repeating collation
G10L  15/32 210 E	3	0	5D015	G10L  15/32	216	ܾȹȰۤʤɸѥ㡥Ѥͽ	Preselection using reference templates, e.g. syllable numbers, which are different from actual collation
G10L  15/32 210 F	3	0	5D015	G10L  15/32	156	ܾȹȰۤʤ륢르ꥺѤͽ	Preselection using algorithm which is different from actual collation
G10L  15/32 210 G	3	0	5D015	G10L  15/32	86	ܾȹȰۤʤħ̤Ѥͽ	Preselection using feature quantities which are different from actual collation
G10L  15/32 210 Z	3	0	5D015	G10L  15/32	279	¾Τ	Others
G10L  15/32 220 \	3	3	5D015	G10L  15/32	1	ʣβǧ֤ʻ	using plural speech recognition apparatuses simultaneously
G10L  15/32 220 A	3	0	5D015	G10L  15/32	77	üԡüǧ	Unspecified or specified speaker recognition apparatus
G10L  15/32 220 B	3	0	5D015	G10L  15/32	81	ñ᡿ñǧ	Monosyllable or word recognition apparatus
G10L  15/32 220 C	3	0	5D015	G10L  15/32	28	ΩϢ³ǧ	Isolated or continuous speech recognition apparatus
G10L  15/32 220 Z	3	0	5D015	G10L  15/32	482	¾Τ	Others
G10L  15/34  \	2	2	5D015	G10L  15/34	5	ñβǧ֤ؤŬѡ㡥ޥץåޤϥ饦ɥԥ塼ƥ󥰤ѤˤΡΣ	Adaptation of a single recogniser for parallel processing, e.g. by use of multiple processors or cloud computing [2013.01]
G10L  15/34 200 \	3	3	5D015	G10L  15/34	54	ѥץ饤Ԥ	using pipeline processing
G10L  15/34 210 \	3	3	5D015	G10L  15/34	71	Ԥ	using parallel processing
G10L  17/00  \	0	0	5D015	G10L  17/00	86	üԼ̤ޤϾȹ絻ѡΣ	Speaker identification or verification techniques[2013.01]
G10L  17/00 153 \	1	1	5D015	G10L  17/00	41	üǧޤüԾȹħͭ	characterised by speaker identification or collation
G10L  17/00 200 \	2	2	5D015	G10L  17/00	12	ħѤ	using speech features
G10L  17/00 200 B	2	0	5D015	G10L  17/00	130	ʣħѤΡ㡥ԥåȥץȥѤ	using a plurality of features, e.g. using pitch and cepstrum
G10L  17/00 200 C	2	0	5D015	G10L  17/00	1188	ȯƤ˰¸ʤΡ㡥եޥȤʿ	Contents of vocalisation being independent, e.g. formant average
G10L  17/00 200 D	2	0	5D015	G10L  17/00	574	ȯƤθѤΡ㡥žֹ桤̾ޤϥѥɤѤ	using language information for contents of vocalisation, e.g. personal identification numbers, names, or password
G10L  17/00 200 Z	2	0	5D015	G10L  17/00	743	¾Τ	Others
G10L  17/00 300 \	2	2	5D015	G10L  17/00	55	ʣβǧ르ꥺѤ	using a plurality of speech recognition algorithm
G10L  17/00 400 \	2	2	5D015	G10L  17/00	296	ʳħѤΡ㡥ǧǧޤɮǧѤ	Utilization of the characteristics other than voice, e.g. the facial recognition, fingerprint recognition or handwriting recognition
G10L  17/02  \	1	1	5D015	G10L  17/02	272	㡥򡨥ѥɽޤϥǥ벽㡥ȽʬϡΣ̣ģϤޤϼʬ˴ŤΡħޤСΣ	Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction [2013.01]
G10L  17/04  \	1	1	5D015	G10L  17/04	298	ؽȤޤϥǥ빽ۡΣ	Training, enrolment or model building [2013.01]
G10L  17/06  \	1	1	5D015	G10L  17/06	135	ջַ굻ѡѥ󡦥ޥåάΣ	Decision making techniques; Pattern matching strategies [2013.01]
G10L  17/08  \	2	2	5D015	G10L  17/08	138	ѥɸѥȤδ֤εΥޤĤߤѤΡΣ	Use of distortion metrics or a particular distance between probe pattern and reference templates [2013.01]
G10L  17/10  \	2	2	5D015	G10L  17/10	119	ޥ⡼륷ƥࡤʣǧ󥸥ޤϥѡȥƥͻ˴ŤΡΣ	Multimodal systems, i.e. based on the integration of multiple recognition engines or fusion of expert systems [2013.01]
G10L  17/12  \	2	2	5D015	G10L  17/12	27	Σ	Score normalisation [2013.01]
G10L  17/14  \	2	2	5D015	G10L  17/14	78	üԤǧޤϸβǤʬޤϲǧλѡΣ	Use of phonemic categorisation or speech recognition prior to speaker recognition or verification [2013.01]
G10L  17/16  \	1	1	5D015	G10L  17/16	30	ޥ륳եǥΣȣͣ͡ϡΣ	Hidden Markov models [HMM] [2013.01]
G10L  17/18  \	1	1	5D015	G10L  17/18	128	͹˥塼롦ͥåȥͥ˥ȡץΣ	Artificial neural networks; Connectionist approaches [2013.01]
G10L  17/20  \	1	1	5D015	G10L  17/20	18	ƥδ뤿ΥѥѴ㡥ͥ뻨ޤϰۤʤưĶФΡΣ	Pattern transformations or operations aimed at increasing system robustness, e.g. against channel noise or different working conditions [2013.01]
G10L  17/22  \	1	1	5D015	G10L  17/22	53	÷硨ޥޥ󡦥󥿡եΣ	Interactive procedures; Man-machine interfaces [2013.01]
G10L  17/24  \	2	2	5D015	G10L  17/24	124	桼ѥɤޤϤ餫줿ȯ褦¥ΡΣ	&nbsp;the user being prompted to utter a password or a predefined phrase [2013.01]
G10L  17/26  \	1	1	5D015	G10L  17/26	68	üʲħǧ㡥ȯѤΤΡưʪǧΣ	Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices [2013.01]
G10L  19/00  \	0	0	5D045	G10L  19/00	138	Ĺ򸺤餹βޤϲʬϹѡ㡥ܥˤ롨ޤϲΥɲޤϥǥɲե륿ǥޤϿʬϤѤΡʳڴˤΣǣȡˡΣ	Speech or audio signal analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals,&nbsp;using source filter models or psychoacoustic analysis (in musical instruments G10H) [7,2013.01]
G10L  19/00 100 \	1	1	5D045	G10L  19/00	107	沽оݤȤʤ벻Ϥ˴ؤ	Relating to input of voice signal which is object of encoding processing
G10L  19/00 200 \	1	1	5D045	G10L  19/00	11	沽˴ؤ	Relating to voice encoding process
G10L  19/00 214 \	2	2	5D045	G10L  19/00	5	ȣͣ͵ѤѤ沽	Voice coding technique that uses HMM technology
G10L  19/00 220 \	2	2	5D045	G10L  19/00	7	ּȷФ벻沽	Voice coding of the waveforms on the time axis
G10L  19/00 220 A	2	0	5D045	G10L  19/00	265	ħ	Characterized by processing
G10L  19/00 220 B	2	1	5D045	G10L  19/00	354	ʬ沽	Differential coding processing
G10L  19/00 220 C	2	2	5D045	G10L  19/00	131	ӥåȥǥ沽	One bit audio signal encoding processing
G10L  19/00 220 E	2	1	5D045	G10L  19/00	244	Ŭ沽	Adaptive coding process
G10L  19/00 220 F	2	1	5D045	G10L  19/00	607	ͽ¬沽	Predictive coding process
G10L  19/00 220 H	2	0	5D045	G10L  19/00	75	ϩħ	Characterized by circuit
G10L  19/00 220 Z	2	0	5D045	G10L  19/00	136	¾Τ	Others
G10L  19/00 240 \	2	2	5D045	G10L  19/00	359	ΰŹ沽	Crypto Graphic technology of voice signal
G10L  19/00 250 \	2	2	5D045	G10L  19/00	485	¾ν	Other processing
G10L  19/00 300 \	1	1	5D045	G10L  19/00	22	沽ܤФ㡥	Post treatment to signal that encoding processing is performed, e.g. transmission
G10L  19/00 310 \	2	2	5D045	G10L  19/00	42	Ͽ˴ؤ	Relating to recording
G10L  19/00 311 \	3	3	5D045	G10L  19/00	299	Ū˴ؤ뵻	Technology relating to static memory
G10L  19/00 312 \	4	4	5D045	G10L  19/00	2	ưޤϺ˴ؤ뵻	Technology relating in-operation or in-reproduction
G10L  19/00 312 A	4	0	5D045	G10L  19/00	133	Ÿ˴ؤ	Relating to power supply management
G10L  19/00 312 B	4	0	5D045	G10L  19/00	387	ǡž˴ؤ뵻	Technology concerning transmission of data
G10L  19/00 312 C	4	0	5D045	G10L  19/00	585	Ͽΰ˴ؤ뵻	Technology concerning recording area
G10L  19/00 312 D	4	0	5D045	G10L  19/00	98	ν˴ؤ뵻	Technology concerning the order of processing
G10L  19/00 312 E	4	0	5D045	G10L  19/00	1249	ˡ˴ؤ뵻	Technology concerning reproducing method
G10L  19/00 312 F	4	0	5D045	G10L  19/00	427	¾ν㡥νȴϢ	Relating to other process, e.g. video signal process
G10L  19/00 312 G	4	0	5D045	G10L  19/00	260	ХåեѤ	Technology that uses buffer
G10L  19/00 312 Z	4	0	5D045	G10L  19/00	669	¾Τ	Others
G10L  19/00 313 \	4	4	5D045	G10L  19/00	2	ʬ¤ˤʤäƤ	Memory unit being conveyable
G10L  19/00 313 A	4	0	5D045	G10L  19/00	79	ȴ˴ؤ뵻	Technology concerning inserting and removing
G10L  19/00 313 B	4	0	5D045	G10L  19/00	85	ƥ˴ؤ뵻	Technology concerning security
G10L  19/00 313 Z	4	0	5D045	G10L  19/00	328	¾Τ	Others
G10L  19/00 314 \	4	4	5D045	G10L  19/00	539	Ū֤ι¤˴ؤΡ㡥å	Relating to overall structure of static memory reproduction device, e.g. arrangement of switches
G10L  19/00 320 \	2	2	5D045	G10L  19/00	65	沽ɾ˴ؤ	Relating to evaluation of coded signal
G10L  19/00 330 \	2	2	5D045	G10L  19/00	3	沽Ф	Processing on coded signal sequence
G10L  19/00 330 A	2	0	5D045	G10L  19/00	329	ʤޤϥץȥ˴ؤΡ㡥ͣУţǡãţ̣Фޤϣǣ	Relating to standard and protocol, e.g. MPEG, CELP, and G72x
G10L  19/00 330 B	2	0	5D045	G10L  19/00	1577	Ѥ˴ؤ	Relating to using of supplementary information
G10L  19/00 330 C	2	0	5D045	G10L  19/00	325	ХåեѤˤϢ³ΤΤΡ㡥֣塡򡡣ɣ	For noncontiguous transmission using buffer, e.g. voice over IP
G10L  19/00 330 D	2	0	5D045	G10L  19/00	216	Ѵ˴ؤ	Relating to code conversion
G10L  19/00 330 F	2	0	5D045	G10L  19/00	133	ʼѡ㡥İΤ˲	Variable in signal quality, e.g. deteriorating voice signal for audition or the like
G10L  19/00 330 Z	2	0	5D045	G10L  19/00	292	¾Τ	Others
G10L  19/00 400 \	1	1	5D045	G10L  19/00	7	沽֤κ	Details of encoder
G10L  19/00 400 A	1	0	5D045	G10L  19/00	466	ϩħ	Characterized by circuit
G10L  19/00 400 B	1	0	5D045	G10L  19/00	80	۾˴ؤ뵻	Technology concerning fault
G10L  19/00 400 C	1	0	5D045	G10L  19/00	0	ŵʤѤ	Using non-electricity means
G10L  19/00 400 Z	1	0	5D045	G10L  19/00	546	¾Τ	Others
G10L  19/00 500 \	1	1	5D045	G10L  19/00	1	沽ѤŬѤ	Applying encoding technique
G10L  19/00 500 A	1	0	5D045	G10L  19/00	78	ܥѤƥ	System using vocoder
G10L  19/00 500 B	1	0	5D045	G10L  19/00	7	ʬ	Speech analysis
G10L  19/00 500 Z	1	0	5D045	G10L  19/00	24	¾Τ	Others
G10L  19/002  \	1	1	5D045	G10L  19/002	191	ưŪӥåȳơγвѣǣ̣ˡΣ	Dynamic bit allocation (for perceptual audio coders G10L 19/032) [2013.01]
G10L  19/005  \	1	1	5D045	G10L  19/005	792	沽르ꥺबϢȤΡͥ顼Σ	Correction of errors induced by the transmission channel, if related to the coding algorithm [2013.01]
G10L  19/008  \	1	1	5D045	G10L  19/008	1321	ޥͥ륪ǥ沽ڤ沽֤ͥδطѤƾĹ򸺾Ρ㡥祤ȥƥ쥪ƥ󥷥ƥ沽ϥޥȥꥭ󥰡Σ	Multichannel audio signal coding or decoding using interchannel correlation to reduce redundancy, e.g. joint-stereo, intensity-coding or matrixing [2013.01]
G10L  19/008 100 \	2	2	5D045	G10L  19/008	1111	ɾѤΡ㡥£ã	using side information, e.g. BCC
G10L  19/008 200 \	2	2	5D045	G10L  19/008	447	֥沽	Object coding
G10L  19/012  \	1	1	5D045	G10L  19/012	345	եȥΥ̵沽Σ	Comfort noise or silence coding [2013.01]
G10L  19/018  \	1	1	5D045	G10L  19/018	884	ǥƩʤԲİǡΥǥؤߡΣ	Audio watermarking, i.e. embedding inaudible data in the audio signal [2013.01]
G10L  19/02  \	1	1	5D045	G10L  19/02	39	ڥȥʬϤѤΡ㡥Ѵܥޤϥ֥ХɥܥΣ	using spectral analysis, e.g. transform vocoders or subband vocoders [7,2013.01]
G10L  19/02 150 \	2	2	5D045	G10L  19/02	1676	沽㡥沽ޥͥ沽¾沽ȴϢΡͽ¬ѤȤȹ礻եޥåѴޤ沽ˡڤ괹	Varous encoding processing, e.g. hierarchical coding, multichannel coding, other coding process, combination with predictive technique, format conversion, and change of coding method.
G10L  19/02 160 \	2	2	5D045	G10L  19/02	1	沽֤κ	Details of encoder
G10L  19/02 160 A	2	0	5D045	G10L  19/02	330	ϩħ	Characterized by circuit
G10L  19/02 160 B	2	0	5D045	G10L  19/02	1	֤ΰ۾Ф	Formalfunction of device
G10L  19/02 160 C	2	0	5D045	G10L  19/02	0	ŵŪѤѤ	Using non-electrical technique
G10L  19/02 160 Z	2	0	5D045	G10L  19/02	91	¾Τ	Others
G10L  19/02 170 \	2	2	5D045	G10L  19/02	3	˴ؤ	Relating to reproduction process
G10L  19/02 170 A	2	0	5D045	G10L  19/02	99	ü˴ؤΡ㡥	Relating to special reproduction, e.g. fast-forwarding
G10L  19/02 170 B	2	0	5D045	G10L  19/02	78	黻̤θΤΤ	For reduction of operation amount
G10L  19/02 170 C	2	0	5D045	G10L  19/02	24	ãУդ٤򸫤ƽƤѹ	Changing processing content according to load of CPU
G10L  19/02 170 Z	2	0	5D045	G10L  19/02	289	¾	Others
G10L  19/02 180 \	2	2	5D045	G10L  19/02	0	ԽѤ˴ؤ	Relating to edit technology
G10L  19/02 180 A	2	0	5D045	G10L  19/02	62	ղ	Addition of control information
G10L  19/02 180 B	2	0	5D045	G10L  19/02	58	ǡΰħΡ㡥ե	Characterized by data processing, e.g. operation of scale factor
G10L  19/02 180 Z	2	0	5D045	G10L  19/02	39	¾Τ	Others
G10L  19/022  \	2	2	5D045	G10L  19/022	196	֥åʤΰɸܤΥ롼ײʬϥɥ򡨥СåװҡΣ	Blocking, i.e. grouping of samples in time; Choice of analysis windows; Overlap factoring [2013.01]
G10L  19/025  \	3	3	5D045	G10L  19/025	113	֡ȿʬǽڤؤ뤿βϡΩ夬θСΣ	Detection of transients or attacks for time/frequency resolution switching [2013.01]
G10L  19/028  \	2	2	5D045	G10L  19/028	53	Υִ㡥Υˤڥȥʬִ³ŪΤΥեȥΥǣ̣ˡΣ	Noise substitution, e.g. substituting non-tonal spectral components by noisy source (comfort noise for discontinuous speech transmission G10L 19/012) [2013.01]
G10L  19/03  \	2	2	5D045	G10L  19/03	74	ץꥨɻߤΤΥڥȥͽ¬ŪʥΥԥ󥰡ΣԣΣӡϡ㡥ͣУţǣޤϣͣУţǣˤΡΣ	Spectral prediction for preventing pre-echo; Temporary noise shaping [TNS], e.g. in MPEG2 or MPEG4 [2013.01]
G10L  19/032  \	2	2	5D045	G10L  19/032	240	ڥȥʬ̻Ҳޤϵ̻ҲΣ	Quantisation or dequantisation of spectral components [2013.01]
G10L  19/032 100 \	3	3	5D045	G10L  19/032	1	ʬ¤ؤƽ뵻	Technology that rearrange component
G10L  19/032 100 A	3	0	5D045	G10L  19/032	1	̵ͭδ¤ؤ	Rearranging by standard of sound and silent
G10L  19/032 100 B	3	0	5D045	G10L  19/032	33	ȡʬΥʬδ¤ؤ	Rearranging by standard of tone component and noise component
G10L  19/032 100 Z	3	0	5D045	G10L  19/032	72	¾Τ	Others
G10L  19/035  \	3	3	5D045	G10L  19/035	3	顼̻ҲΣ	Scalar quantisation [2013.01]
G10L  19/035  A	3	0	5D045	G10L  19/035	257	ե沽ؿɽޤ̻Ҳ󥸤	Setting normalization process, coding of scale factor, exponent and mantisa expression part, and quantization range
G10L  19/035  B	3	1	5D045	G10L  19/035	338	Ŭӥåȳƽ㡥ȿӰΥӥåʬ	Adaptive bit allocation process[Bit distribution or the like for each frequency band]
G10L  19/035  C	3	1	5D045	G10L  19/035	44	;ӥåȤγƽ˴ؤ	Relating to allocation of surplus bit
G10L  19/035  D	3	1	5D045	G10L  19/035	133	ӥåȳƤδ˴ؤΡ㡥ӥåȥ졼¤ޤϸܲѳ	Relating to standard of allocation, e.g. bit rate limitation, fixation + variable allocation or the like
G10L  19/035  E	3	1	5D045	G10L  19/035	152	ޥͤηޤϺǾİͤη	Determination of masking threshold and determination of threshold of audibility
G10L  19/035  Z	3	0	5D045	G10L  19/035	188	¾Τ	Others
G10L  19/038  \	3	3	5D045	G10L  19/038	288	٥ȥ̻Ҳ㡥ԣ֣ѥǥΣ	Vector quantisation, e.g. TwinVQ audio [2013.01]
G10L  19/04  \	1	1	5D045	G10L  19/04	16	ͽ¬ѤѤΡΣ	using predictive techniques [7,2013.01]
G10L  19/06  \	2	2	5D045	G10L  19/06	1	ڥȥħФޤϥɲ㡥ûͽ¬Σ	Determination or coding of the spectral characteristics, e.g. of the short-term prediction coefficients [7,2013.01]
G10L  19/06  B	2	0	5D045	G10L  19/06	502	̣Уåܥ	LPC vocoder
G10L  19/06  Z	2	0	5D045	G10L  19/06	236	¾Τ	Others
G10L  19/07  \	3	3	5D045	G10L  19/07	181	ڥȥСΣ̣ӣСϥܥΣ	Line spectrum pair [LSP] vocoders [2013.01]
G10L  19/08  \	2	2	5D045	G10L  19/08	6	忶ǽФޤϥɲĹͽ¬ѥ᡼ФޤϥɲΣ	Determination or coding of the excitation function; Determination or coding of the long-term prediction parameters [7,2013.01]
G10L  19/08  F	2	0	5D045	G10L  19/08	139	ɥ֥åκ˴ؤ	Relating to creation of code book
G10L  19/08  G	2	0	5D045	G10L  19/08	354	ɥ֥åõ˴ؤ	Relating to search of code book
G10L  19/08  Z	2	0	5D045	G10L  19/08	176	¾Τ	Others
G10L  19/083  \	3	3	5D045	G10L  19/083	82	忶ǽ忶ǤΡʣǣ̣ͥˡΣ	the excitation function being an excitation gain () [2013.01]
G10L  19/087  \	3	3	5D045	G10L  19/087	84	忶ǥѤΡ㡥ͣţ̣Сͣ£šʬӰ̣Уäޤϣȣ֣أáΣ	using mixed excitation models, e.g. MELP, MBE, split band LPC&nbsp;or HVXC [2013.01]
G10L  19/09  \	3	3	5D045	G10L  19/09	268	Ĺͽ¬ʤŪĹν㡥Ŭɥ֥åޤϥԥåͽ¬ѤΡΣ	Long term prediction, i.e. removing periodical redundancies, e.g. by using adaptive codebook or pitch predictor [2013.01]
G10L  19/093  \	3	3	5D045	G10L  19/093	87	忶ǥѤΡΣ	using sinusoidal excitation models [2013.01]
G10L  19/097  \	3	3	5D045	G10L  19/097	25	ץȥפȷʬޤȷ沽ΣУףɡϤѤΡΣ	using prototype waveform decomposition or prototype waveform interpolative [PWI] coders [2013.01]
G10L  19/10  \	3	3	5D045	G10L  19/10	265	忶ǽޥѥ륹忶ǤΡΣ	the excitation function being a multipulse excitation [7,2013.01]
G10L  19/107  \	4	4	5D045	G10L  19/107	109	ѡѥ륹忶㡥Ūɥ֥åѤΡΣ	Sparse pulse excitation, e.g. by using algebraic codebook [2013.01]
G10L  19/113  \	4	4	5D045	G10L  19/113	16	쥮顼ѥ륹忶Σ	Regular pulse excitation [2013.01]
G10L  19/12  \	3	3	5D045	G10L  19/12	281	忶ǽ忶ǤΡ㡥忶ͽ¬Σãţ̣СϥܥΣ	the excitation function being a code excitation, e.g. in code excited linear prediction [CELP] vocoders [7,2013.01]
G10L  19/125  \	4	4	5D045	G10L  19/125	186	ԥå忶㡥ԥåƱ忶ãţ̣СΣ	Pitch excitation, e.g. pitch synchronous innovation CELP [PSI-CELP]&nbsp; [2013.01]
G10L  19/13  \	4	4	5D045	G10L  19/13	54	ĺ忶ͽ¬Σ	Residual excited linear prediction [RELP] [2013.01]
G10L  19/135  \	4	4	5D045	G10L  19/135	40	٥ȥ忶ͽ¬Σ	Vector sum excited linear prediction [VSELP] [2013.01]
G10L  19/16  \	2	2	5D045	G10L  19/16	64	ܥΥƥΣ	Vocoder architecture [2013.01]
G10L  19/16 100 \	3	3	5D045	G10L  19/16	0	沽˴ؤ뵻	Technology concerning encoding processing
G10L  19/16 100 A	3	0	5D045	G10L  19/16	295	٥ȥ̻ҲѤ˴ؤ	Relating to vector quantization technology
G10L  19/16 100 Z	3	0	5D045	G10L  19/16	426	¾Τ	Others
G10L  19/16 200 \	3	3	5D045	G10L  19/16	1	沽֤κ	Details of encoder
G10L  19/16 200 A	3	0	5D045	G10L  19/16	166	ϩħ	characterized by circuit
G10L  19/16 200 B	3	0	5D045	G10L  19/16	27	۾Ф	relating to abnormality
G10L  19/16 200 Z	3	0	5D045	G10L  19/16	86	¾Τ	Others
G10L  19/18  \	3	3	5D045	G10L  19/18	105	ʣΥ⡼ɤѤܥΣ	Vocoders using multiple modes [2013.01]
G10L  19/20  \	4	4	5D045	G10L  19/20	218	μ̤ͭ沽ϥ֥å沽ޤϥ֥ȥ١沽ѤΡΣ	using sound class specific coding, hybrid encoders or object based coding [2013.01]
G10L  19/22  \	4	4	5D045	G10L  19/22	236	⡼ɤηꡤʤѥ᡼Ф륪ǥƤ˴ŤΡΣ	Mode decision, i.e. based on audio signal content versus external parameters [2013.01]
G10L  19/24  \	4	4	5D045	G10L  19/24	193	ѥ졼ȥǥå㡥Ū沽ޤؾ沽Τ褦ʥ֥ɽѤưۤʤʼ뤿ΤΡΣ	Variable rate codecs, e.g. for generating different qualities using a scalable representation such as hierarchical encoding or layered encoding [2013.01]
G10L  19/26  \	2	2	5D045	G10L  19/26	7	ץ졦ե륿󥰤ޤϥݥȡե륿󥰡Σ	Pre-filtering or post-filtering [2013.01]
G10L  19/26  A	2	0	5D045	G10L  19/26	88	ץե륿󥰡㡥沽ιȿĴ	Prefiltering, e.g. High frequency emphasis before coding
G10L  19/26  B	2	0	5D045	G10L  19/26	264	ݥȥե륿󥰡㡥¦ǤΥԥåĴեޥȶĴ	Post filtering, e.g. pitch emphasis and format emphasis at decoding side
G10L  19/26  Z	2	0	5D045	G10L  19/26	65	¾Τ	Others
G10L  21/00  \	0	0	5D045	G10L  21/00	14	λ٤ѹ뤿ˡ¾βİޤԲİ桤㡥пޤϿп桤벻ѡʣǣ̣ͥˡΣ	Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility  (G10L 19/00 takes precedence)[2013.01]
G10L  21/003  \	1	1	5D045	G10L  21/003	334	ѹΡ㡥ԥåޤϥեޥȡΣ	Changing voice quality, e.g. pitch or formants [2013.01]
G10L  21/007  \	2	2	5D045	G10L  21/007	879	ħΡΣ	characterised by the process used [2013.01]
G10L  21/01  \	3	3	5D045	G10L  21/01	107	ּѹΣ	Correction of time axis [2013.01]
G10L  21/013  \	3	3	5D045	G10L  21/013	423	ɸΥԥåؤŬΣ	Adapting to target pitch [2013.01]
G10L  21/02  \	1	1	5D045	G10L  21/02	187	ζĴ㡥㸺ޤϥͭˤ륨㸺ȣ£ϥ󥺥ե꡼äˤ륨ȣͣˡΣ	Speech enhancement, e.g. noise reduction or echo cancellation (reducing echo effects in line transmission systems H04B 3/20; echo suppression in hands-free telephones H04M 9/08) [7,2013.01]
G10L  21/0208  \	2	2	5D045	G10L  21/0208	74	Σ	Noise filtering [2013.01]
G10L  21/0208 100 \	3	3	5D045	G10L  21/0208	11	ϩħ	characterized by circuit
G10L  21/0208 100 A	3	0	5D045	G10L  21/0208	473	ϼʡ㡥ޥ˴ؤ	relating to means for inputting voice, e.g. michrophone
G10L  21/0208 100 B	3	0	5D045	G10L  21/0208	736	ե륿˴ؤ	relating to filter
G10L  21/0208 100 Z	3	0	5D045	G10L  21/0208	502	¾Τ	Others
G10L  21/0216  \	3	3	5D045	G10L  21/0216	204	οΤѤˡħΡΣ	characterised by the method used for estimating noise [2013.01]
G10L  21/0224  \	4	4	5D045	G10L  21/0224	497	ּǽΡΣ	Processing in the&nbsp;time domain [2013.01]
G10L  21/0232  \	4	4	5D045	G10L  21/0232	1051	ȿǽΡΣ	Processing in the&nbsp;frequency domain [2013.01]
G10L  21/0264  \	3	3	5D045	G10L  21/0264	4	ѥ᡼¬μħΡ㡥صѡ򺹵Ѥޤͽ¬ѡΣ	characterised by the type of parameter measurement, e.g. correlation techniques, zero crossing techniques or predictive techniques [2013.01]
G10L  21/0264  A	3	0	5D045	G10L  21/0264	125	ص	Correlation technique
G10L  21/0264  B	3	0	5D045	G10L  21/0264	5	򺵵	Zero crossing technique
G10L  21/0264  C	3	0	5D045	G10L  21/0264	57	ͽ¬	Predictive technique
G10L  21/0264  Z	3	0	5D045	G10L  21/0264	376	¾Τ	Others
G10L  21/0272  \	2	2	5D045	G10L  21/0272	47	ʬΥΣ	Voice signal separating [2013.01]
G10L  21/0272 100 \	3	3	5D045	G10L  21/0272	8	ϩħ	characterised by circuits
G10L  21/0272 100 A	3	0	5D045	G10L  21/0272	309	ϼʡ㡥ޥ˴ؤ	relating to input means of speech, e.g. microphone
G10L  21/0272 100 B	3	0	5D045	G10L  21/0272	247	ե륿˴ؤ	relating to filter
G10L  21/0272 100 Z	3	0	5D045	G10L  21/0272	284	¾Τ	Others
G10L  21/028  \	3	3	5D045	G10L  21/028	14	ѤΡΣ	using properties of sound source [2013.01]
G10L  21/028  A	3	0	5D045	G10L  21/028	35	ο	One sound source
G10L  21/028  B	3	0	5D045	G10L  21/028	436	οʣ	Multiple sound sources
G10L  21/028  C	3	1	5D045	G10L  21/028	126	ʣβ֤ؤѤ	using the correlation between multiple sound sources
G10L  21/028  Z	3	0	5D045	G10L  21/028	89	¾Τ	Oothers
G10L  21/0308  \	3	3	5D045	G10L  21/0308	8	ѥ᡼¬μħΡ㡥صѡ򺹵Ѥޤͽ¬ѡΣ	characterised by the type of parameter measurement, e.g. correlation techniques, zero crossing techniques or predictive techniques [2013.01]
G10L  21/0308  A	3	0	5D045	G10L  21/0308	63	ص	Correlation techniques
G10L  21/0308  B	3	0	5D045	G10L  21/0308	2	򺵵	Zero crossing techniques
G10L  21/0308  C	3	0	5D045	G10L  21/0308	16	ͽ¬	Predictive techniques
G10L  21/0308  Z	3	0	5D045	G10L  21/0308	361	¾Τ	Others
G10L  21/0316  \	2	2	5D045	G10L  21/0316	141	ѹΡΣ	by changing the amplitude [2013.01]
G10L  21/0316 100 \	3	3	5D045	G10L  21/0316	86	ϩħ	characterised by circuits
G10L  21/0324  \	3	3	5D045	G10L  21/0324	226	κΣ	Details of processing therefor [2013.01]
G10L  21/0332  \	4	4	5D045	G10L  21/0332	335	ȷѲΡΣ	involving modification of waveforms [2013.01]
G10L  21/034  \	4	4	5D045	G10L  21/034	684	ưĴΤΡΣ	Automatic adjustment [2013.01]
G10L  21/0356  \	3	3	5D045	G10L  21/0356	35	¾οƱԤΤΡ㡥Σ	for synchronising with other signals, e.g. video signals [2013.01]
G10L  21/0364  \	3	3	5D045	G10L  21/0364	512	ʹ䤹뤿ΤΡΣ	for improving intelligibility [2013.01]
G10L  21/038  \	2	2	5D045	G10L  21/038	144	ӰĥѤѤΡΣ	using band spreading techniques [2013.01]
G10L  21/0388  \	3	3	5D045	G10L  21/0388	578	κΣ	Details of processing therefor [2013.01]
G10L  21/0388 100 \	4	4	5D045	G10L  21/0388	425	ϩħ	characterised by circuits
G10L  21/04  \	1	1	5D045	G10L  21/04	375	ְ̤ޤϳĥΣ	Time compression or expansion [7,2013.01]
G10L  21/043  \	2	2	5D045	G10L  21/043	499	®٤ѹˤΡΣ	by changing speed [2013.01]
G10L  21/043 100 \	3	3	5D045	G10L  21/043	250	ϩħ	characterised by circuits
G10L  21/045  \	3	3	5D045	G10L  21/045	218	ȷδְޤѤΡΣ	using thinning out or insertion of a waveform [2013.01]
G10L  21/047  \	4	4	5D045	G10L  21/047	236	ְޤȷΥפħΡΣ	characterised by the type of waveform to be thinned out or inserted [2013.01]
G10L  21/049  \	4	4	5D045	G10L  21/049	133	ȷ³ħΤΡΣ	characterised by the interconnection of waveforms [2013.01]
G10L  21/055  \	2	2	5D045	G10L  21/055	101	¾οȤƱԤΤΡ㡥Σ	for synchronising with other signals, e.g. video signals [2013.01]
G10L  21/057  \	2	2	5D045	G10L  21/057	302	ʹ䤹뤿ΤΡΣ	for improving intelligibility [2013.01]
G10L  21/06  \	1	1	5D045	G10L  21/06	15	ԲİɽؤѴ㡥βĻ벽ޤϿФΤβʣǣ̣ͥˡΣ	Transformation of speech into a non-audible representation, e.g. speech visualisation or speech processing for tactile aids () [7,2013.01]
G10L  21/06 400 \	2	2	5D045	G10L  21/18	1	ϩħ	Characterized by circuit
G10L  21/06 400 A	2	0	5D045	G10L  21/06	1	ŵѤ	Using non-electrical mechanism
G10L  21/06 400 Z	2	0	5D045	G10L  21/06	6	¾	Others
G10L  21/06 500 \	2	2	5D045	G10L  21/06	43	ϿԽ뤿Τ	For editing input signal
G10L  21/10  \	2	2	5D045	G10L  21/10	169	ĻѴΡΣ	Transforming into visible information [2013.01]
G10L  21/12  \	3	3	5D045	G10L  21/12	185	ּɽΡΣ	by displaying time domain information [2013.01]
G10L  21/14  \	3	3	5D045	G10L  21/14	132	ȿɽΡΣ	by displaying frequency domain information [2013.01]
G10L  21/16  \	2	2	5D045	G10L  21/16	59	ԲĻѴΡʼδԤľܤİФ¾μγФȼ费뤳ȤǤ褦ˤ֤ޤˡƣˡΣ	Transforming into a non-visible representation (devices or methods enabling ear patients to replace direct auditory perception by another kind of perception A61F 11/04) [2013.01]
G10L  21/18  \	2	2	5D045	G10L  21/18	17	ѴκΣ	Details of the transformation process [2013.01]
G10L  25/00  \	0	0	5D045	G10L  25/00	26	ǣ̣ǣ̣Υ롼Τɤ줫Ĥ˸ꤵʤʬϵѡʿ̤ħФ줿硤㡥̵֤Ф줿硤ȾƳ̵ȣǣˡΣ	Speech or voice analysis techniques not restricted to a single one of groups G10L 15/00-G10L 21/00?(muting semiconductor-based amplifiers when some special characteristics of a signal are sensed by a speech detector, e.g. sensing when no signal is present, H03G 3/34)[2013.01]
G10L  25/03  \	1	1	5D045	G10L  25/03	447	Фѥ᡼ΥפħΤΡΣ	characterised by the type of extracted parameters [2013.01]
G10L  25/06  \	2	2	5D045	G10L  25/06	415	Фѥ᡼طǤΡΣ	the extracted parameters being correlation coefficients [2013.01]
G10L  25/09  \	2	2	5D045	G10L  25/09	152	Фѥ᡼򺹿ǤΡΣ	the extracted parameters being zero crossing rates [2013.01]
G10L  25/12  \	2	2	5D045	G10L  25/12	258	Фѥ᡼ͽ¬ǤΡΣ	the extracted parameters being prediction coefficients [2013.01]
G10L  25/15  \	2	2	5D045	G10L  25/15	263	Фѥ᡼եޥȾǤΡΣ	the extracted parameters being formant information [2013.01]
G10L  25/18  \	2	2	5D045	G10L  25/18	1108	Фѥ᡼ӰΥڥȥǤΡΣ	the extracted parameters being spectral information of each sub-band [2013.01]
G10L  25/21  \	2	2	5D045	G10L  25/21	757	Фѥ᡼ѥǤΡΣ	the extracted parameters being power information [2013.01]
G10L  25/24  \	2	2	5D045	G10L  25/24	181	Фѥ᡼ץȥǤΡΣ	the extracted parameters being the cepstrum [2013.01]
G10L  25/27  \	1	1	5D045	G10L  25/27	283	ʬϼˡħΡΣ	characterised by the analysis technique [2013.01]
G10L  25/27 100 \	2	2	5D045	G10L  25/27	38	沽Ѥ˴ؤ	relating coding technique
G10L  25/27 200 \	2	2	5D045	G10L  25/27	16	ŵŪʤѤ	using non-electrical means
G10L  25/30  \	2	2	5D045	G10L  25/30	806	˥塼롦ͥåȥѤΡΣ	using neural networks [2013.01]
G10L  25/33  \	2	2	5D045	G10L  25/33	12	եѤΡΣ	using fuzzy logic [2013.01]
G10L  25/36  \	2	2	5D045	G10L  25/36	13	ѤΡΣ	using chaos theory [2013.01]
G10L  25/39  \	2	2	5D045	G10L  25/39	16	Ū르ꥺѤΡΣ	using genetic algorithms [2013.01]
G10L  25/45  \	1	1	5D045	G10L  25/45	151	ʬΥפħΤΡΣ	characterised by the type of analysis window [2013.01]
G10L  25/48  \	1	1	5D045	G10L  25/48	93	ӤäŬ礷ΡΣ	specially adapted for particular use [2013.01]
G10L  25/48 100 \	2	2	5D045	G10L  25/48	338	ʬϷ̤ɽ˴ؤΡȷɽǣ̣ǣ̣	relating to displaying result of analysis (Display of waveform G10L21/06-G01L21/18)
G10L  25/51  \	2	2	5D045	G10L  25/51	1248	ӤޤȽ̤ΤΤΡΣ	for comparison or discrimination [2013.01]
G10L  25/51 100 \	3	3	5D045	G10L  25/51	692	饪	Karaoke scoring
G10L  25/51 200 \	3	3	5D045	G10L  25/51	12	ޥθξ	Failure of microphone
G10L  25/51 300 \	3	3	5D045	G10L  25/51	749	ڲ㡥ޤϥƥݡμ̤˴ؤ	relating to identification of musical information, e.g. genre and tempo
G10L  25/51 400 \	3	3	5D045	G10L  25/51	639		estimation of sound source direction
G10L  25/54  \	3	3	5D045	G10L  25/54	403	ΤΤΡΣ	for retrieval [2013.01]
G10L  25/57  \	3	3	5D045	G10L  25/57	301	ưνΤΤΡΣ	for processing of video signals [2013.01]
G10L  25/60  \	3	3	5D045	G10L  25/60	278	ομ¬ꤹ뤿ΤΡΣ	for measuring the quality of voice signals [2013.01]
G10L  25/63  \	3	3	5D045	G10L  25/63	607	ꤹ뤿ΤΡΣ	for estimating an emotional state [2013.01]
G10L  25/66  \	3	3	5D045	G10L  25/66	219	򹯾֤˴ؤѥ᡼Ф뤿ΤΡʿǤΤθФޤ¬£ˡΣ	for extracting parameters related to health condition (detecting or measuring for diagnostic purposes A61B 5/00) [2013.01]
G10L  25/69  \	2	2	5D045	G10L  25/69	179	ޤϥǥɤɾ뤿ΤΡΣ	for evaluating synthetic or decoded voice signals [2013.01]
G10L  25/72  \	2	2	5D045	G10L  25/72	8	ʬϷ̤뤿ΤΡΣ	for transmitting results of analysis [2013.01]
G10L  25/72  A	2	0	5D045	G10L  25/72	72	ѥޥå󥰥ܥ	Pattern matching vocoder
G10L  25/72  Z	2	0	5D045	G10L  25/72	49	¾Τ	Others
G10L  25/75  \	1	1	5D045	G10L  25/75	155	ƻѥ᡼ǥ벽뤿ΤΡΣ	for modelling vocal tract parameters [2013.01]
G10L  25/78  \	1	1	5D045	G10L  25/78	1184	ο̵ͭθСˤ롢ȿˤڤ괹ʣȣͣˡΣ	Detection of presence or absence of voice signals (switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M 9/10) [2013.01]
G10L  25/81  \	2	2	5D045	G10L  25/81	253	ڤȲȽ̤뤿ΤΡΣ	for discriminating voice from music [2013.01]
G10L  25/84  \	2	2	5D045	G10L  25/84	654	ȲȽ̤뤿ΤΡΣ	for discriminating voice from noise [2013.01]
G10L  25/87  \	2	2	5D045	G10L  25/87	91	οϢ³θСΣ	Detection of discrete points within a voice signal [2013.01]
G10L  25/90  \	1	1	5D045	G10L  25/90	1293	ΥԥåСΣ	Pitch determination of speech signals [2013.01]
G10L  25/93  \	1	1	5D045	G10L  25/93	343	̵ͭʬ̡ʣǣ̣ͥˡΣ	Discriminating between voiced and unvoiced parts of speech signals () [2013.01]
G10L  99/00  \	0	0	5D045	G10L  99/00	0	Υ֥饹¾Υ롼פʬवʤΣ	Subject matter not provided for in other groups of this subclass [2013.01]
