Open Access

Audio-Visual Speech Recognition Using Lip Information Extracted from Side-Face Images

  • Koji Iwano1Email author,
  • Tomoaki Yoshinaga1,
  • Satoshi Tamura1 and
  • Sadaoki Furui1
EURASIP Journal on Audio, Speech, and Music Processing20072007:064506

https://doi.org/10.1155/2007/64506

Received: 12 July 2006

Accepted: 25 January 2007

Published: 15 March 2007

Abstract

This paper proposes an audio-visual speech recognition method using lip information extracted from side-face images as an attempt to increase noise robustness in mobile environments. Our proposed method assumes that lip images can be captured using a small camera installed in a handset. Two different kinds of lip features, lip-contour geometric features and lip-motion velocity features, are used individually or jointly, in combination with audio features. Phoneme HMMs modeling the audio and visual features are built based on the multistream HMM technique. Experiments conducted using Japanese connected digit speech contaminated with white noise in various SNR conditions show effectiveness of the proposed method. Recognition accuracy is improved by using the visual information in all SNR conditions. These visual features were confirmed to be effective even when the audio HMM was adapted to noise by the MLLR method.

[123456789101112131415161718192021]

Authors’ Affiliations

(1)
Department of Computer Science, Tokyo Institute of Technology

References

  1. Bregler C, Konig Y: "Eigenlips" for robust speech recognition. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '94), April 1994, Adelaide, SA, Australia 2: 669-672.Google Scholar
  2. Tomlinson MJ, Russell MJ, Brooke NM: Integrating audio and visual information to provide highly robust speech recognition. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '96), May 1996, Atlanta, Ga, USA 2: 821-824.Google Scholar
  3. Potamianos G, Cosatto E, Graf HP, Roe DB: Speaker independent audio-visual database for bimodal ASR. Proceedings of ESCA Workshop on Audio-Visual Speech Processing (AVSP '97), September 1997, Rhodes, Greece 65-68.Google Scholar
  4. Neti C, Potamianos G, Luettin J, et al.: Audio-visual speech recognition. In Final Workshop 2000 Report. Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, Md, USA; 2000.Google Scholar
  5. Dupont S, Luettin J: Audio-visual speech modeling for continuous speech recognition. IEEE Transactions on Multimedia 2000,2(3):141-151. 10.1109/6046.865479View ArticleGoogle Scholar
  6. Zhang Y, Levinson S, Huang TS: Speaker independent audio-visual speech recognition. Proceedings of IEEE International Conference on Multi-Media and Expo (ICME '00), July-August 2000, New York, NY, USA 1073-1076.Google Scholar
  7. Chu SM, Huang TS: Bimodal speech recognition using coupled hidden Markov models. Proceedings of the 6th International Conference on Spoken Language Processing (ICSLP '00), October 2000, Beijing, China 2: 747-750.Google Scholar
  8. Miyajima C, Tokuda K, Kitamura T: Audio-visual speech recognition using MCE-based HMMs and model-dependent stream weights. Proceedings of the 6th International Conference on Spoken Language Processing (ICSLP '00), October 2000, Beijing, China 2: 1023-1026.Google Scholar
  9. Iwano K, Tamura S, Furui S: Bimodal speech recognition using lip movement measured by optical-flow analysis. Proceedings of International Workshop on Hands-Free Speech Communication (HSC '01), April 2001, Kyoto, Japan 187-190.Google Scholar
  10. Tamura S, Iwano K, Furui S: Multi-modal speech recognition using optical-flow analysis for lip images. Journal of VLSI Signal Processing—Systems for Signal, Image, and Video Technology 2004,36(2-3):117-124.View ArticleGoogle Scholar
  11. Tamura S, Iwano K, Furui S: Improvement of audio-visual speech recognition in cars. Proceedings of the 18th International Congress on Acoustics (ICA '04), April 2004, Kyoto, Japan 4: 2595-2598.Google Scholar
  12. Yoshinaga T, Tamura S, Iwano K, Furui S: Audio-visual speech recognition using new lip features extracted from side-face images. Proceedings of COST278 and ISCA Tutorial and Research Workshop (ITRW) on Robustness Issues in Conversational Interaction (Robust '04), August 2004, Norwich, UKGoogle Scholar
  13. Yoshinaga T, Tamura S, Iwano K, Furui S: Audio-visual speech recognition using lip movement extracted from side-face images. Proceedings of International Conference on Audio-Visual Speech Processing, ISCA Tutorial and Research Workshop (AVSP '03), September 2003, St. Jorioz, France 117-120.Google Scholar
  14. Bovik AC, Desai MD: Basic binary image processing. In Handbook of Image and Video Processing. Edited by: Bovik AC. Academic Press, San Diego, Calif, USA; 2000:37-52.Google Scholar
  15. Horn BKP, Schunck BG: Determining optical flow. Artificial Intelligence 1981,17(1–3):185-203.View ArticleGoogle Scholar
  16. Leggetter CJ, Woodland PC: Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Computer Speech and Language 1995,9(2):171-185. 10.1006/csla.1995.0010View ArticleGoogle Scholar
  17. Lucey P, Potamianos G: Lipreading using profile versus frontal views. Proceedings of the 8th IEEE Workshop on Multimedia Signal Processing (MMSP '06), October 2006, Victoria, BC, Canada 24-28.Google Scholar
  18. Potamianos G, Graf HP: Discriminative training of HMM stream exponents for audio-visual speech recognition. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '98), May 1998, Seattle, Wash, USA 6: 3733-3736.Google Scholar
  19. Nakamura S, Ito H, Shikano K: Stream weight optimization of speech and lip image sequence for audio-visual speech recognition. Proceedings of 6th International Conference on Spoken Language Processing (ICSLP '00), October 2000, Beijing, China 3: 20-24.Google Scholar
  20. Tamura S, Iwano K, Furui S: A stream-weight optimization method for audio-visual speech recognition using multi-stream HMMs. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '04), May 2004, Montreal, Quebec, Canada 1: 857-860.Google Scholar
  21. Tamura S, Iwano K, Furui S: A stream-weight optimization method for multi-stream HMMs based on likelihood value normalization. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '05), March 2005, Philadelphia, Pa, USA 1: 469-472.Google Scholar

Copyright

© Koji Iwano et al. 2007

This article is published under license to BioMed Central Ltd. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.