KR20000071367A - 음성 인식 시스템 및 방법 - Google Patents
음성 인식 시스템 및 방법 Download PDFInfo
- Publication number
- KR20000071367A KR20000071367A KR1020000008455A KR20000008455A KR20000071367A KR 20000071367 A KR20000071367 A KR 20000071367A KR 1020000008455 A KR1020000008455 A KR 1020000008455A KR 20000008455 A KR20000008455 A KR 20000008455A KR 20000071367 A KR20000071367 A KR 20000071367A
- Authority
- KR
- South Korea
- Prior art keywords
- noise
- model
- training
- pronunciation
- recognition
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 27
- 238000012549 training Methods 0.000 claims abstract description 31
- 238000005259 measurement Methods 0.000 claims abstract description 8
- 230000001186 cumulative effect Effects 0.000 description 17
- 239000013598 vector Substances 0.000 description 16
- 230000007704 transition Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/10—Speech classification or search using distance or distortion measures between unknown speech and reference templates
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/14—Speech classification or search using statistical models, e.g. Hidden Markov Models [HMMs]
- G10L15/142—Hidden Markov Models [HMMs]
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/20—Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Telephonic Communication Services (AREA)
- Electrically Operated Instructional Devices (AREA)
- Machine Translation (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Control Of Amplification And Gain Control (AREA)
- Interconnected Communication Systems, Intercoms, And Interphones (AREA)
Abstract
Description
Claims (10)
- 음성 인식 시스템을 동작시키는 방법에 있어서,트레이닝(training) 동안 측정된 적어도 하나의 배경 잡음 레벨과 동작 인식 모드(recognition mode) 동안 이루어진 입력 발음동안의 잡음 신호 측정치의 함수로서 가변적인 거부 엄격성(rejection strictness)을 발생시키는 단계; 및상기 가변적인 거부 엄격성의 함수로서 단어 엔트런스 패널티(word entrance penalty)를 유도하는 단계를 포함하는 것을 특징으로 하는 방법.
- 제1항에 있어서,상기 가변적인 거부 엄격성을 발생시키는 단계는 한 모델에 대해 트레이닝 발음 중 적어도 일부 동안 잡음을 측정하는 단계를 포함하는 것을 특징으로 하는 방법.
- 제1항에 있어서,상기 트레이닝 발음으로부터 잡음 특성을 선택적으로 업데이트하는 단계를 더 포함하는 것을 특징으로 하는 방법.
- 제1항에 있어서,잡음 통계가 인식 알고리즘에 이용가능하도록 모델의 트레이닝 동안 잡음 통계를 저장하는 단계를 더 포함하는 것을 특징으로 하는 방법.
- 제3항에 있어서,핸즈프리 모드(hands-free mode)로 트레이닝시에는 잡음 통계를 업데이트하지 않는 것을 특징으로 하는 방법.
- 제3항에 있어서,신호 대 잡음비를 발생시키는 단계를 더 포함하고, 상기신호 대 잡음비가 소정의 레벨 이하이면, 상기 트레이닝을 금지하는 것을 특징으로 하는 방법.
- 제1항에 있어서,인식하는 동안, 한 발음에 대해 잡음 통계가 이용가능하지 않으면, 정렬 알고리즘을 상기 발음에 적용할 때 인식 알고리즘이 최소 엄격성 요건으로 디폴트(default) 상태가 되는 것을 특징으로 하는 방법.
- 제1항에 있어서,인식하는 동안, 입력 잡음 에너지 특성을 기준 잡음 통계에 비교하고, 잡음비를 계산하는 것을 특징으로 하는 방법.
- 제8항에 있어서,어휘외(out of vocabulary) 거부 알고리즘의 엄격성은 잡음비를 근거로 선택되는 것을 특징으로 하는 방법.
- 제1항에 있어서,음성 태그 모델(voice tag model)과 병렬로 0 평균 1 상태 가비지 모델(zero mean one state garbage model)을 사용해 최상 경로의 신뢰 측정을 실시하는 것을 특징으로 하는 방법.
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US9/256,279 | 1999-02-23 | ||
US09/256,279 US6275800B1 (en) | 1999-02-23 | 1999-02-23 | Voice recognition system and method |
US09/256,279 | 1999-02-23 |
Publications (2)
Publication Number | Publication Date |
---|---|
KR20000071367A true KR20000071367A (ko) | 2000-11-25 |
KR100321565B1 KR100321565B1 (ko) | 2002-01-23 |
Family
ID=22971635
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020000008455A KR100321565B1 (ko) | 1999-02-23 | 2000-02-22 | 음성 인식 시스템 및 방법 |
Country Status (8)
Country | Link |
---|---|
US (1) | US6275800B1 (ko) |
JP (1) | JP4354072B2 (ko) |
KR (1) | KR100321565B1 (ko) |
CN (1) | CN1171201C (ko) |
BR (2) | BRPI0001268B1 (ko) |
DE (1) | DE10006930B4 (ko) |
GB (1) | GB2347252B (ko) |
MX (1) | MXPA00001875A (ko) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7617168B2 (en) | 2005-10-11 | 2009-11-10 | Samsung Electronics Co., Ltd. | Apparatus and method for controlling portable device |
Families Citing this family (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE19811879C1 (de) * | 1998-03-18 | 1999-05-12 | Siemens Ag | Einrichtung und Verfahren zum Erkennen von Sprache |
US6577997B1 (en) | 1999-05-28 | 2003-06-10 | Texas Instruments Incorporated | System and method of noise-dependent classification |
DE60018696T2 (de) * | 1999-07-01 | 2006-04-06 | Koninklijke Philips Electronics N.V. | Robuste sprachverarbeitung von verrauschten sprachmodellen |
US6778959B1 (en) * | 1999-10-21 | 2004-08-17 | Sony Corporation | System and method for speech verification using out-of-vocabulary models |
US6754629B1 (en) * | 2000-09-08 | 2004-06-22 | Qualcomm Incorporated | System and method for automatic voice recognition using mapping |
EP1215654B1 (en) | 2000-12-13 | 2006-05-24 | Sony Deutschland GmbH | Method for recognizing speech |
US7941313B2 (en) * | 2001-05-17 | 2011-05-10 | Qualcomm Incorporated | System and method for transmitting speech activity information ahead of speech features in a distributed voice recognition system |
US7203643B2 (en) * | 2001-06-14 | 2007-04-10 | Qualcomm Incorporated | Method and apparatus for transmitting speech activity in distributed voice recognition systems |
DE10133333C1 (de) * | 2001-07-10 | 2002-12-05 | Fraunhofer Ges Forschung | Verfahren und Vorrichtung zum Erzeugen eines Fingerabdrucks und Verfahren und Vorrichtung zum Identifizieren eines Audiosignals |
JP3678421B2 (ja) * | 2003-02-19 | 2005-08-03 | 松下電器産業株式会社 | 音声認識装置及び音声認識方法 |
JP4497834B2 (ja) * | 2003-04-28 | 2010-07-07 | パイオニア株式会社 | 音声認識装置及び音声認識方法並びに音声認識用プログラム及び情報記録媒体 |
US9093073B1 (en) * | 2007-02-12 | 2015-07-28 | West Corporation | Automatic speech recognition tagging |
US9020816B2 (en) * | 2008-08-14 | 2015-04-28 | 21Ct, Inc. | Hidden markov model for speech processing with training method |
CN105321518B (zh) * | 2014-08-05 | 2018-12-04 | 中国科学院声学研究所 | 一种低资源嵌入式语音识别的拒识方法 |
CN107112011B (zh) * | 2014-12-22 | 2021-11-09 | 英特尔公司 | 用于音频特征提取的倒谱方差归一化 |
CN105575386B (zh) * | 2015-12-18 | 2019-07-30 | 百度在线网络技术(北京)有限公司 | 语音识别方法和装置 |
KR20200063521A (ko) | 2018-11-28 | 2020-06-05 | 삼성전자주식회사 | 전자 장치 및 이의 제어 방법 |
CN115631743B (zh) * | 2022-12-07 | 2023-03-21 | 中诚华隆计算机技术有限公司 | 一种基于语音芯片的高精度语音识别方法及系统 |
Family Cites Families (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB8608289D0 (en) * | 1986-04-04 | 1986-05-08 | Pa Consulting Services | Noise compensation in speech recognition |
JPH03203488A (ja) * | 1989-12-29 | 1991-09-05 | Pioneer Electron Corp | 音声リモートコントロール装置 |
CA2042926C (en) * | 1990-05-22 | 1997-02-25 | Ryuhei Fujiwara | Speech recognition method with noise reduction and a system therefor |
JPH04182700A (ja) * | 1990-11-19 | 1992-06-30 | Nec Corp | 音声認識装置 |
US5386492A (en) * | 1992-06-29 | 1995-01-31 | Kurzweil Applied Intelligence, Inc. | Speech recognition system utilizing vocabulary model preselection |
JPH07273840A (ja) * | 1994-03-25 | 1995-10-20 | Nec Corp | 音声帯域制御機能を有する移動電話機 |
US5832430A (en) * | 1994-12-29 | 1998-11-03 | Lucent Technologies, Inc. | Devices and methods for speech recognition of vocabulary words with simultaneous detection and verification |
DE19521258A1 (de) * | 1995-06-10 | 1996-12-12 | Philips Patentverwaltung | Spracherkennungssystem |
US5778342A (en) * | 1996-02-01 | 1998-07-07 | Dspc Israel Ltd. | Pattern recognition system and method |
JP3452443B2 (ja) * | 1996-03-25 | 2003-09-29 | 三菱電機株式会社 | 騒音下音声認識装置及び騒音下音声認識方法 |
US5960397A (en) * | 1997-05-27 | 1999-09-28 | At&T Corp | System and method of recognizing an acoustic environment to adapt a set of based recognition models to the current acoustic environment for subsequent speech recognition |
JPH11126090A (ja) * | 1997-10-23 | 1999-05-11 | Pioneer Electron Corp | 音声認識方法及び音声認識装置並びに音声認識装置を動作させるためのプログラムが記録された記録媒体 |
US5970446A (en) * | 1997-11-25 | 1999-10-19 | At&T Corp | Selective noise/channel/coding models and recognizers for automatic speech recognition |
-
1999
- 1999-02-23 US US09/256,279 patent/US6275800B1/en not_active Expired - Lifetime
-
2000
- 2000-02-14 GB GB0003269A patent/GB2347252B/en not_active Expired - Lifetime
- 2000-02-16 DE DE10006930A patent/DE10006930B4/de not_active Expired - Lifetime
- 2000-02-17 BR BRPI0001268A patent/BRPI0001268B1/pt not_active IP Right Cessation
- 2000-02-17 BR BRPI0001268A patent/BRPI0001268B8/pt unknown
- 2000-02-22 KR KR1020000008455A patent/KR100321565B1/ko active IP Right Grant
- 2000-02-23 JP JP2000045353A patent/JP4354072B2/ja not_active Expired - Fee Related
- 2000-02-23 MX MXPA00001875A patent/MXPA00001875A/es active IP Right Grant
- 2000-02-23 CN CNB001024094A patent/CN1171201C/zh not_active Expired - Lifetime
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7617168B2 (en) | 2005-10-11 | 2009-11-10 | Samsung Electronics Co., Ltd. | Apparatus and method for controlling portable device |
Also Published As
Publication number | Publication date |
---|---|
BRPI0001268B8 (pt) | 2017-11-07 |
DE10006930A1 (de) | 2000-09-28 |
CN1264892A (zh) | 2000-08-30 |
GB2347252A (en) | 2000-08-30 |
CN1171201C (zh) | 2004-10-13 |
KR100321565B1 (ko) | 2002-01-23 |
US6275800B1 (en) | 2001-08-14 |
BRPI0001268B1 (pt) | 2017-05-09 |
GB0003269D0 (en) | 2000-04-05 |
GB2347252B (en) | 2001-03-28 |
JP2000242294A (ja) | 2000-09-08 |
MXPA00001875A (es) | 2004-09-10 |
BR0001268A (pt) | 2000-10-10 |
DE10006930B4 (de) | 2004-08-26 |
JP4354072B2 (ja) | 2009-10-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR100321565B1 (ko) | 음성 인식 시스템 및 방법 | |
KR100719650B1 (ko) | 잡음 신호에서 음성의 엔드포인팅 방법 | |
KR100321464B1 (ko) | 음성 인식 시스템에서 특성을 추출하는 방법 | |
US6223155B1 (en) | Method of independently creating and using a garbage model for improved rejection in a limited-training speaker-dependent speech recognition system | |
US6134527A (en) | Method of testing a vocabulary word being enrolled in a speech recognition system | |
US20050049865A1 (en) | Automatic speech clasification | |
EP1220197A2 (en) | Speech recognition method and system | |
WO2008058842A1 (en) | Voice activity detection system and method | |
US6961702B2 (en) | Method and device for generating an adapted reference for automatic speech recognition | |
JP2003202887A (ja) | 音声認識装置、音声認識方法及び音声認識プログラム | |
RU2127912C1 (ru) | Способ обнаружения и кодирования и/или декодирования стационарных фоновых звуков и устройство для кодирования и/или декодирования стационарных фоновых звуков | |
JP5988077B2 (ja) | 発話区間検出装置及び発話区間検出のためのコンピュータプログラム | |
US6233557B1 (en) | Method of selectively assigning a penalty to a probability associated with a voice recognition system | |
JP2003241788A (ja) | 音声認識装置及び音声認識システム | |
JP2001520764A (ja) | スピーチ分析システム | |
Taboada et al. | Explicit estimation of speech boundaries | |
US20080228477A1 (en) | Method and Device For Processing a Voice Signal For Robust Speech Recognition | |
JP4749990B2 (ja) | 音声認識装置 | |
KR100647291B1 (ko) | 음성의 특징을 이용한 음성 다이얼링 장치 및 방법 | |
KR100278640B1 (ko) | 이동 전화기를 위한 음성 다이얼링 장치 및방법 | |
Beritelli et al. | A robust low-complexity algorithm for voice command recognition in adverse acoustic environments | |
JP2008225001A (ja) | 音声認識装置および音声認識方法,音声認識用プログラム | |
JP2001092487A (ja) | 音声認識方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
E701 | Decision to grant or registration of patent right | ||
GRNT | Written decision to grant | ||
FPAY | Annual fee payment |
Payment date: 20121227 Year of fee payment: 12 |
|
FPAY | Annual fee payment |
Payment date: 20131227 Year of fee payment: 13 |
|
FPAY | Annual fee payment |
Payment date: 20141223 Year of fee payment: 14 |
|
FPAY | Annual fee payment |
Payment date: 20151224 Year of fee payment: 15 |
|
FPAY | Annual fee payment |
Payment date: 20161229 Year of fee payment: 16 |
|
FPAY | Annual fee payment |
Payment date: 20171228 Year of fee payment: 17 |
|
FPAY | Annual fee payment |
Payment date: 20181221 Year of fee payment: 18 |