Classifier-based non-linear projection for continuous speech...

Details Classifier-based non-linear projection for continuous speech... Classifier-based non-linear projection for continuous speech...

2007-07-10

2007-07-10

Hudspeth, David (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

For storage or transmission

C704S233000

Reexamination Certificate

active

10196768

ABSTRACT:
A method segments an audio signal including frames into non-speech and speech segments. First, high-dimensional spectral features are extracted from the audio signal. The high-dimensional features are then projected non-linearly to low-dimensional features that are subsequently averaged using a sliding window and weighted averages. A linear discriminant is applied to the averaged low-dimensional features to determine a threshold separating the low-dimensional features. The linear discriminant can be determined from a Gaussian mixture or a polynomial applied to a bi-model histogram distribution of the low-dimensional features. Then, the threshold can be used to classify the frames into either non-speech or speech segments. Speech segments having a very short duration can be discarded, and the longer speech segments can be further extended. In batch-mode or real-time the threshold can be updated continuously.

REFERENCES:
patent: 5276766 (1994-01-01), Bahl et al.
patent: 5754681 (1998-05-01), Watanabe et al.
patent: 6226408 (2001-05-01), Sirosh
patent: 6556967 (2003-04-01), Nelson et al.
patent: 6862567 (2005-03-01), Gao
patent: 2005/0065793 (2005-03-01), Choi et al.
Singh, R. Seltzer, M. Raj, B. Stern, R. “Speech in Noisy Environments: robust automatic segmentation, feature extraction, and hypothesis combination”, Acoustics, Speech and Signal processing, May 2001, pp. 273-276.
Raj, B. Singh, R. Stern, R. “Interference of Missing Spectrographic Features for Robust Speech Recognition” Proc 5th International conference on spoken language processing, 1999.
Sun, D. “Feature dimension reduction using reduced-rank maximum estimation for hidden markov models” Spoken language ICSLP pp. 244-247 1996.
Hermansky, H. Sharma, S. Jain, P. “Data-derived nonlinear mapping for feature extraction in HMM” in Proc. ICASSP 2000 Istanbul.
Kocsor, A. Kuba, A. Toth, L. “Phoneme Classification Using Kernel Principle Component Analysis” Periodica Polytechnica Electrical Engineering, 2000, vol. 44, No. 1, p. 77-90.
Lamel, L., Rabiner, L.R., Rosenberg, A., and Wilpon, J., “An improved endpoint detector for isolated word recognition,” IEEE ASSP magazine, vol. 29, 777-785, 1981.
Junqua, J.-C., Mak, B., and Reaves, B., “A robust algorithm for word boundary detection in the presence of noise,” IEEE trans. on Speech and Audio Proc., vol. 2, No. 3, 406-412, 1994.
Hain, T., and Woodland, P.C., “Segmentation and classification of broadcast news audio,” Proceedings of the International conference on speech and language processing ICSLP98, pp. 2727-2730, 1998.
Siegler, M., Jain, U., Raj, B., and Stern, R.M., “Automatic segmentation, classification and clustering of broadcast news audio,” Proceedings of the DARPA speech recognition workshop Feb. 1997, pp. 97-99, 1997.
Viterbi, A.J., “Error bounds for convolutional codes and an asymptotically optimum decoding algorithm,” IEEE Trans. on Information theory, 260-269, 1967.
Leggetter, C.J., and Woodland, P.C., “Speaker adaptation of HMMs using linear regression,” Technical report CUED/F-INFENG/TR. 181, Cambridge University, 1994.
Doh, S.-J., “Enhancements to transformation-based speaker adaptation: principal component and inter-class maximum likelihood linear regression,” Ph.D thesis, Carnegie Mellon University, 2000.

Affiliated with

Also associated with

Rating

Classifier-based non-linear projection for continuous speech... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Classifier-based non-linear projection for continuous speech..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Classifier-based non-linear projection for continuous speech... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3725632