Robust Endpoint Detection
Often the first step in speech signal processing is the use of endpoint detection to separate speech and silence signals for further processing. This topic has been studied for several decades; however, as wireless communications and VoIP phones are becoming more and more popular, more background and system noises are affecting communication channels, which poses a challenge to the existing algorithms; therefore new and robust algorithms are needed.
KeywordsEnergy Normalization Automatic Speech Recognition Speaker Recognition Voice Over Internet Protocol Word Error Rate
Unable to display preview. Download preview PDF.
- 4.Brodsky, B., Darkhovsky, B. S.: Nonparametric methods in change-point problems. Kluwer Academic, Boston (1993)Google Scholar
- 5.Bullington, K., Fraser, J. M.: “Engineering aspects of TASI,” Bell Syst. Tech. J. pp. 353–364, Mar 1959Google Scholar
- 8.Chengalvarayan, R.: “Robust energy normalization using speech/nonspeech discriminator for German connected digit recognition,” in Proceedings of Eurospeech’99, (Budapest), pp. 61–64, Sept. 1999Google Scholar
- 9.Chou, W., Lee, C.-H., Juang, B.-H.: “Minimum error rate training of inter-word context dependent acoustic model units in speech recognition,” in Proceedings of Int. Conf. on Spoken Language Processing, pp. 432–439, 1994Google Scholar
- 11.Haigh, J. A., Mason, J. S.: “Robust voice activity detection using cepstral features,” in Proceedings of IEEE TENCON (China), pp. 321–324, 1993Google Scholar
- 12.Junqua, J. C., Reaves, B., Mak, B.: “A study of endpoint detection algorithms in adverse conditions: Incidence on a DTW and HMM recognize,” in Proceedings of Eurospeech, pp. 1371–1374, 1991Google Scholar
- 16.Li, Q. and Tsai, A.: “A language-independent personal voice controller with embedded speaker verification,” in Eurospeech’99 (Budapest, Hungary), Sept. 1999Google Scholar
- 17.Li, Q. and Tsai, A.: “A matched filter approach to endpoint detection for robust speaker verification,” in Proceedings of IEEE Workshop on Automatic Identification (Summit, NJ), Oct. 1999Google Scholar
- 19.Li, Q., Zheng, J., Zhou, Q., and Lee, C.-H.: “A robust, real-time endpoint detector with energy normalization for ASR in adverse environments,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (Salt Lake City), May 2001Google Scholar
- 21.Rabiner, L., Juang, B.-H.: Fundamentals of speech recognition. PTR Prentice Hall, Englewood Cliffs (1993)Google Scholar
- 22.Rabiner, L. R., Sambur, M. R.: “An algorithm for determining the endpoints of isolated utterances”. The Bell System Technical Journal 54, 297–315 (1975)Google Scholar
- 26.Wilpon, J. G., Rabiner, L. R., Martin, T.: “An improved word-detection algorithm for telephone-quality speech incorporating both syntactic and semantic constraints”. AT&T Bell Laboratories Technical Journal 63, 479–498 (1984)Google Scholar