Skip to content

Advertisement

  • Research Article
  • Open Access

A Posterior Union Model with Applications to Robust Speech and Speaker Recognition

EURASIP Journal on Advances in Signal Processing20062006:075390

https://doi.org/10.1155/ASP/2006/75390

  • Received: 13 January 2005
  • Accepted: 14 December 2005
  • Published:

Abstract

This paper investigates speech and speaker recognition involving partial feature corruption, assuming unknown, time-varying noise characteristics. The probabilistic union model is extended from a conditional-probability formulation to a posterior-probability formulation as an improved solution to the problem. The new formulation allows the order of the model to be optimized for every single frame, thereby enhancing the capability of the model for dealing with nonstationary noise corruption. The new formulation also allows the model to be readily incorporated into a Gaussian mixture model (GMM) for speaker recognition. Experiments have been conducted on two databases: TIDIGITS and SPIDRE, for speech recognition and speaker identification. Both databases are subject to unknown, time-varying band-selective corruption. The results have demonstrated the improved robustness for the new model.

Keywords

  • Information Technology
  • Mixture Model
  • Quantum Information
  • Speech Recognition
  • Gaussian Mixture Model

[1234567891011121314151617181920212223242526]

Authors’ Affiliations

(1)
School of Computer Science, Queen's University Belfast, Belfast, BT7 1NN, United Kingdom
(2)
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, 610054, China

References

  1. Lippmann RP, Carlson BA: Using missing feature theory to actively select features for robust speech recognition with interruptions, filtering and noise. Proceedings of 5th European Conference on Speech Communication and Technology (Eurospeech '97), September 1997, Rhodes, Greece 37-40.Google Scholar
  2. Tibrewala S, Hermansky H: Sub-band based recognition of noisy speech. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97), April 1997, Munich, Germany 2: 1255-1258.Google Scholar
  3. Drygajlo A, El-Maliki M: Speaker verification in noisy environments with combined spectral subtraction and missing feature theory. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '98), May 1998, Seattle, Wash, USA 1: 121-124.Google Scholar
  4. Okawa S, Bocchieri E, Potamianos A: Multi-band speech recognition in noisy environments. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '98), May 1998, Seattle, Wash, USA 2: 641-644.Google Scholar
  5. Renevey P, Drygajlo A: Statistical estimation of unreliable features for robust speech recognition. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '00), June 2000, Istanbul, Turkey 3: 1731-1734.Google Scholar
  6. Besacier L, Bonastre JF, Fredouille C: Localization and selection of speaker-specific information with statistical modeling. Speech Communication 2000, 31(2-3):89-106. 10.1016/S0167-6393(99)00070-9View ArticleGoogle Scholar
  7. Seltzer ML, Raj B, Stern RM: Classifier-based mask estimation for missing feature methods of robust speech recognition. Proceedings of International Conference on Spoken Language Processing (ICSLP '00), October 2000, Beijing, ChinaGoogle Scholar
  8. Barker J, Cooke MP, Green P: Robust ASR based on clean speech models: an evaluation of missing data techniques for connected digit recognition in noise. Proceedings of 7th European Conference on Speech Communication and Technology (Eurospeech '01), September 2001, Aalborg, Denmark 213-217.Google Scholar
  9. Morris A, Hagen A, Glotin H, Bourlard H: Multi-stream adaptive evidence combination for noise robust ASR. Speech Communication 2001, 34(1-2):25-40. 10.1016/S0167-6393(00)00044-3View ArticleMATHGoogle Scholar
  10. Cooke MP, Green P, Josifovski L, Vizinho A: Robust automatic speech recognition with missing and unreliable acoustic data. Speech Communication 2001, 34(3):267-285. 10.1016/S0167-6393(00)00034-0View ArticleMATHGoogle Scholar
  11. Barker JP, Cooke MP, Ellis DPW: Decoding speech in the presence of other sources. Speech Communication 2005, 45(1):5-25. 10.1016/j.specom.2004.05.002View ArticleGoogle Scholar
  12. Ming J, Jan̆covĭc P, Smith FJ: Robust speech recognition using probabilistic union models. IEEE Transactions on Speech and Audio Processing 2002, 10(6):403-414. 10.1109/TSA.2002.803439View ArticleGoogle Scholar
  13. Ming J, Smith FJ: Speech recognition with unknown partial feature corruption—a review of the union model. Computer Speech and Language 2003, 17(2-3):287-305. 10.1016/S0885-2308(03)00003-2View ArticleGoogle Scholar
  14. Jan̆covĭc P, Ming J: A probabilistic union model with automatic order selection for noisy speech recognition. Journal of Acoustic Society of America 2001, 110(3):1641-1648. 10.1121/1.1387083View ArticleGoogle Scholar
  15. Reynolds DA: Speaker identification and verification using Gaussian mixture speaker models. Speech Communication 1995, 17(1-2):91-108. 10.1016/0167-6393(95)00009-DView ArticleGoogle Scholar
  16. Leonard RG: A database for speaker-indpendent digit recognition. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '84), March 1984, San Diego, Calif, USA 42.11.1-42.11.4.Google Scholar
  17. Campbell JP Jr., Reynolds DA: Corpora for the evaluation of speaker recognition systems. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '99), March 1999, Phoenix, Ariz, USA 2: 2247-2250.Google Scholar
  18. Reynolds DA: The effects of handset variability on speaker recognition performance: experiment on the Switchboard corpus. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '96), May 1996, Atlanta, Ga, USA 113-116.Google Scholar
  19. Ortega-Garcia J, Gonzalez-Rodriguez L: Overview of speaker enhancement techniques for automatic speaker recognition. Proceedings of International Conference on Spoken Language Processing (ICSLP '96), October 1996, Philadelphia, Pa, USA 929-932.View ArticleGoogle Scholar
  20. Suhadi , Stan S, Fingscheidt T, Beaugeant C: An evaluation of VTS and IMM for speaker verification in noise. Proceedings of 8th European Conference on Speech Communication and Technology (Eurospeech '03), September 2003, Geneva, Switzerland 1669-1672.Google Scholar
  21. Matsui T, Kanno T, Furui S: Speaker recognition using HMM composition in noisy environments. Computer Speech and Language 1996, 10(2):107-116. 10.1006/csla.1996.0007View ArticleGoogle Scholar
  22. Wong LP, Russell M: Text-dependent speaker verification under noisy conditions using parallel model combination. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '01), May 2001, Salt Lake City, Utah, USA 1: 457-460.Google Scholar
  23. Nadeu C, Hernando J, Gorricho M: On the decorrelation of filter-bank energies in speech recognition. Proceedings of 4th European Conference on Speech Communication and Technology (Eurospeech '95), September 1995, Madrid, Spain 1381-1384.Google Scholar
  24. Paliwal KK: Decorrelated and liftered filter-bank energies for robust speech recognition. Proceedings of 6th European Conference on Speech Communication and Technology (Eurospeech '99), September 1999, Budapest, Hungary 85-88.Google Scholar
  25. Ming J, Smith FJ: A posterior union model for improved robust speech recognition in nonstationary noise. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '03), April 2003, Hong Kong 1: 420-423.View ArticleGoogle Scholar
  26. Ming J: Universal compensation—an approach to noisy speech recognition assuming no knowledge of noise. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '04), May 2004, Montreal, Canada 961-964.Google Scholar

Copyright

© Ming et al. 2006

Advertisement