Speech recognition device and speech recognition method

Details Speech recognition device and speech recognition method Speech recognition device and speech recognition method

2005-03-15

2010-10-12

Chawan, Vijay B (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

For storage or transmission

C704S228000, C704S234000, C704S253000, C704S233000, C381S094700, C381S094300, C381S057000, C381S097000

Reexamination Certificate

active

07813921

ABSTRACT:
There is provided a voice recognition device and a voice recognition method that enhance the function of noise adaptation processing in voice recognition processing and reduce the capacity of a memory being used. Acoustic models are subjected to clustering processing to calculate the centroid of each cluster and the differential vector between the centroid and each model, model composition between each kind of assumed noise model and the calculated centroid is carried out, and the centroid of each composition model and the differential vector are stored in a memory. In the actual recognition processing, the centroid optimal to the environment estimated by the utterance environmental estimation is extracted from the memory, model restoration is carried out on the extracted centroid by using the differential vector stored in the memory, and noise adaptation processing is executed on the basis of the restored model.

REFERENCES:
patent: 4811404 (1989-03-01), Vilmur et al.
patent: 6188982 (2001-02-01), Chiang
patent: 6438513 (2002-08-01), Pastor et al.
patent: 6615170 (2003-09-01), Liu et al.
patent: 6741873 (2004-05-01), Doran et al.
patent: 6766292 (2004-07-01), Chandran et al.
patent: 6859420 (2005-02-01), Coney et al.
patent: 6937980 (2005-08-01), Krasny et al.
patent: 6959276 (2005-10-01), Droppo et al.
patent: 7047047 (2006-05-01), Acero et al.
patent: 7165027 (2007-01-01), Kellner et al.
patent: 7266494 (2007-09-01), Droppo et al.
patent: 2001/0028713 (2001-10-01), Walker
patent: 2003/0040908 (2003-02-01), Yang et al.
patent: 1 189 205 (2002-03-01), None
patent: 1 345 209 (2003-09-01), None
patent: 1 355 296 (2003-10-01), None
patent: 1400952 (2004-03-01), None
patent: 1 471 500 (2004-10-01), None
patent: 9-258765 (1997-10-01), None
patent: 10-149191 (1998-06-01), None
patent: 10-161692 (1998-06-01), None
patent: 2000-330587 (2000-11-01), None
patent: 2002-14692 (2002-01-01), None
patent: 2002-91485 (2002-03-01), None
patent: 2003-330484 (2003-11-01), None
Pellom et al., (“An improved (Auto:I, LSP:T) Constrained Iterative Speech Enhancement for Colored Noise Environments”, IEEE transactions On Speech and Audio Signal Processing, vol. 6, No. 6, Nov. 1998).
Yao et al., (“Noise Adaptive Speech Recognition with Acoustic Models Trained from Noisy Speech Evaluated on Aurora-2 Database”, ICSLP 2002: 7th International Conference on Spoken Language Processing, vol. 4, No. 4, Sep. 2002, pp. 2437-2440).
Akae et al., “Zatsuon Kankyo eno Jacobi Tekioho no Kakucho”, The Acoustical Society of Japan (ASJ) Koen Ronbunshu, 2000 Nen Shunki I, (Mar. 15, 2000), 1-8-4, pp. 7 to 8.
Ida et al., “Zatsuon DB to Model Tekioka o Mochiita HMM Goseiho ni okeru Zatsuon Hendo Taisei no Hyoka”, The Acoustical Society of Japan (ASN) Koen Ronbunshu, 2004 Nen Shuki I, (Oct. 2, 2001), 1-1-17, pp. 33 to 34.
Noguchi et al., “1 Channel Nyuryoku Shingochu no Toppatsusei Zatsuon no Hanbetsu to Jokyo”, The Acoustical Society of Japan (ASJ) Koen Ronbunshu, 2004 Nen Shunki I, (Mar. 17, 2004) 3-P-30, pp. 655 to 656.
European Search Report.
“Noise Adaptive Speech Recognition With Acoustic Models Trained From Noisy Speech Evaluated on Aurora-2 Database”, Kaisheng Yao, et al. ATR Spoken Language Translation Research Laboratories, Kyoto, Japan, ICSLP 2002, vol vol. 4 pp. 2437-2440.

Affiliated with

Also associated with

Rating

Speech recognition device and speech recognition method does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Speech recognition device and speech recognition method, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition device and speech recognition method will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4217957