SG59893G - An adaptive multivariate estimating apparatus - Google Patents
An adaptive multivariate estimating apparatusInfo
- Publication number
- SG59893G SG59893G SG598/93A SG59893A SG59893G SG 59893 G SG59893 G SG 59893G SG 598/93 A SG598/93 A SG 598/93A SG 59893 A SG59893 A SG 59893A SG 59893 G SG59893 G SG 59893G
- Authority
- SG
- Singapore
- Prior art keywords
- classifiers
- statistical
- unvoiced
- weights
- frame
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/93—Discriminating between voiced and unvoiced parts of speech signals
Abstract
Apparatus for detecting a fundamental frequency in speech in a changing speech environment by using adaptive statistical techniques. A statistical voice detector (103) detects changes in the voice environment by classifiers that define certain attributes of the speech to recalculate weights that are used to combine the classifiers in making the unvoiced/voiced decision that specifies whether the speech has a fundamental frequency or not. The detector is responsive to classifiers to first calculate the average of the classifiers (202) and then to determine the overall probability that any frame will be unvoiced. In addition, the detector using a statistical calculator (203) forms two vectors, one vector represents the statistical average of values that an unvoiced frame's classifiers would have and the other vector represents the statistical average of the values of the classifiers for a voiced frame. These latter calculations are performed utilizing not only the average value of the classifiers and present classifiers but also a vector defining the weights that are utilized to determine whether a frame is unvoiced or not plus a threshold value. A weights calculator (204) is responsive to the information generated in the statistical calculations to generate a new set of values for the weights vector and the threshold value which are utilized by the statistical calculator during the next frame. An unvoiced/voiced determinator (205) then is reponsive to the two statistical average vectors and the weights vector to make the unvoiced/voiced decision.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US3429687A | 1987-04-03 | 1987-04-03 | |
PCT/US1988/000030 WO1988007738A1 (en) | 1987-04-03 | 1988-01-12 | An adaptive multivariate estimating apparatus |
Publications (1)
Publication Number | Publication Date |
---|---|
SG59893G true SG59893G (en) | 1993-07-09 |
Family
ID=21875521
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
SG598/93A SG59893G (en) | 1987-04-03 | 1993-05-07 | An adaptive multivariate estimating apparatus |
Country Status (9)
Country | Link |
---|---|
EP (1) | EP0308433B1 (en) |
JP (1) | JPH01502779A (en) |
AT (1) | ATE82426T1 (en) |
AU (1) | AU599459B2 (en) |
CA (2) | CA1337708C (en) |
DE (1) | DE3875894T2 (en) |
HK (1) | HK106693A (en) |
SG (1) | SG59893G (en) |
WO (1) | WO1988007738A1 (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE3876569T2 (en) * | 1987-04-03 | 1993-04-08 | American Telephone & Telegraph | DETECTOR FOR TUNING LOUD WITH ADAPTIVE THRESHOLD. |
JP3277398B2 (en) * | 1992-04-15 | 2002-04-22 | ソニー株式会社 | Voiced sound discrimination method |
US6202046B1 (en) | 1997-01-23 | 2001-03-13 | Kabushiki Kaisha Toshiba | Background noise/speech classification method |
JP3670217B2 (en) | 2000-09-06 | 2005-07-13 | 国立大学法人名古屋大学 | Noise encoding device, noise decoding device, noise encoding method, and noise decoding method |
JP4517045B2 (en) * | 2005-04-01 | 2010-08-04 | 独立行政法人産業技術総合研究所 | Pitch estimation method and apparatus, and pitch estimation program |
CN104517614A (en) * | 2013-09-30 | 2015-04-15 | 上海爱聊信息科技有限公司 | Voiced/unvoiced decision device and method based on sub-band characteristic parameter values |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE3876569T2 (en) * | 1987-04-03 | 1993-04-08 | American Telephone & Telegraph | DETECTOR FOR TUNING LOUD WITH ADAPTIVE THRESHOLD. |
-
1988
- 1988-01-12 JP JP62506332A patent/JPH01502779A/en not_active Withdrawn
- 1988-01-12 EP EP88901347A patent/EP0308433B1/en not_active Expired - Lifetime
- 1988-01-12 WO PCT/US1988/000030 patent/WO1988007738A1/en active IP Right Grant
- 1988-01-12 DE DE8888901347T patent/DE3875894T2/en not_active Expired - Lifetime
- 1988-01-12 AT AT88901347T patent/ATE82426T1/en not_active IP Right Cessation
- 1988-01-12 AU AU12226/88A patent/AU599459B2/en not_active Ceased
- 1988-02-29 CA CA000560109A patent/CA1337708C/en not_active Expired - Fee Related
-
1993
- 1993-05-07 SG SG598/93A patent/SG59893G/en unknown
- 1993-10-07 HK HK1066/93A patent/HK106693A/en not_active IP Right Cessation
-
1995
- 1995-03-09 CA CA000616983A patent/CA1338251C/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
EP0308433A1 (en) | 1989-03-29 |
HK106693A (en) | 1993-10-15 |
AU1222688A (en) | 1988-11-02 |
WO1988007738A1 (en) | 1988-10-06 |
AU599459B2 (en) | 1990-07-19 |
EP0308433B1 (en) | 1992-11-11 |
CA1338251C (en) | 1996-04-16 |
ATE82426T1 (en) | 1992-11-15 |
JPH0795237B1 (en) | 1995-10-11 |
CA1337708C (en) | 1995-12-05 |
DE3875894D1 (en) | 1992-12-17 |
DE3875894T2 (en) | 1993-05-19 |
JPH01502779A (en) | 1989-09-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Beritelli et al. | A robust voice activity detector for wireless communications using soft computing | |
CA2483324A1 (en) | Estimation of background noise in a variable rate vocoder | |
HK1056427A1 (en) | Method and apparatus for constructing voice templates for a speaker-independent voice recognition system. | |
SG59893G (en) | An adaptive multivariate estimating apparatus | |
CN108847218A (en) | A kind of adaptive threshold adjusting sound end detecting method, equipment and readable storage medium storing program for executing | |
US5974381A (en) | Method and system for efficiently avoiding partial matching in voice recognition | |
Silsbee | Sensory integration in audiovisual automatic speech recognition | |
HK21794A (en) | An adaptive threshold voiced detector | |
JP3034279B2 (en) | Sound detection device and sound detection method | |
HoChoi et al. | Speech recognition method using quantised LSP parameters in CELP-type coders | |
Fissore et al. | Analysis and improvement of the partial distance search algorithm | |
JPH04296799A (en) | Voice recognition device | |
Kolano et al. | Combination of vector quantization and Gaussian mixture models for speaker verification with sparse training data | |
KR0170317B1 (en) | Voice recognition method using hidden markov model having distortion density of observation vector | |
Thompson et al. | Within class optimization of cepstra for speaker recognition. | |
Wutiwiwatchai et al. | A new strategy of fuzzy-neural network for Thai numeral speech recognition | |
Yousfi et al. | The centisecond two levels hidden semi markov model (CTLHSMM) | |
Huang et al. | Voice activity detection using haircell model in noisy environment | |
Stringa | An artificial intelligence approach to speech recognition and understanding | |
JPS6136797A (en) | Voice segmentation | |
JPS6479867A (en) | Method and device for determining subject of conversation | |
Wen et al. | Enhancing the stability of speaker verification with compressed templates | |
Merwe et al. | Hybrid combination of knowledge-and cepstral-based features for phoneme recognition | |
Choi et al. | The use of acoustic contextual information in HMM-based speech recognition | |
JPH02293798A (en) | Dictionary updating system for voice recognizing device |