Abstract
We describe an architecture for speech recognition based interactive toys and discuss the strategies we have adopted to deal with the requirements for the speech recognizer imposed by this application. In particular, we focus on the fact that speech recognizers used in interactive toys must deal with users whose age ranges from children to adults. The large variations in vocal tract length between children and adults can significantly degrade the performance of speech recognizers. We compare two approaches to vocal tract length normalization: feature-based VTLN and model-based VTLN. We describe why intuitively, one might expect that due to the coarser frequency information used by the model-based approach, that feature-based VTLN would outperform modelbased VTLN. However, our results indicate that there is very little difference in performance between the two schemes.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Lee, L. and Rose R.,“A frequency warping approach to speaker normalization”, IEEE Transactions on Speech & Audio Processing, vol. 6,no. 1, pp. 49–60, Jan. 1998.
Eide, E. and Gish, H., “A parametric approach to vocal tract length normalization”, Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing, Atlanta, GA, USA, vol. 1, pp. 346–348, 1996.
Wegmann, S., McAllaster, D., Orloff, J. and Peskin, B., “Speaker normalization on conversational telephone speech”, Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing, Atlanta, GA, USA, vol. 1, pp. 339–341, 1996.
Wilpon, J.G. and Jacobsen, C.N., “A study of speech recognition for children and the elderly”, Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing, Atlanta, GA, USA, vol. 1, pp. 349–352, 1996.
Welling, L., Haeb-Umbach, R., Zubert, X. and Haberland, N., “A study on speaker normalization using vocal tract normalization and speaker adaptive training”, Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing, Seattle, WA, USA, vol. 2, pp. 797–800, 1998.
Claes, T., Dologlou, I., ten Bosch, L. and vanCompernolle, D., “A novel feature transformation for vocal tract length normalization in automatic speech recognition”, Speech and Audio Processing, IEEE Transactions, vol. 6,no. 6, pp. 549–557, Nov. 1998.
Cox, S., “Speaker normalization in the MFCC domain”, Proc. 6th International Conference on Spoken Language Processing, Bejiing 2000.
Appleton and Perera, eds., The Development and Practice of Electronic Music, Prentice-Hall, p.42, 1975.
Rabiner, L. R., Fundamentals of Speech Recognition, Prentice-Hall, Inc., 1993.
Wilpon, J.G. and Jacobsen, C.N., “A study of speech recognition for children and the elderly”, Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing, Atlanta, GA, USA, vol. 1, pp. 349–352, 1996.
Rose R. C., “Discriminant wordspotting techniques for rejecting non-vocabulary utterances in unconstrained speech”, Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing, San Francisco, CA, USA, vol. 2, pp. 105–108, 1992.
Knill K. M., Young S. J., “Fast Implementation Methods for Viterbi-Based Word-Spotting”, Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing, Atlanta, GA, USA, vol. 1, pp. 522–525, 1996.
Rose R. C., “Keyword Detection in Conversational Speech Utterances Using Hidden Markov Model Based Continuous Speech Recognition”, Computer Speech and Language, vol. 9,no. 4, pp. 309–333, 1995.
Lai, C.S. and Shi, B. E., “A One-Pass Strategy for Keyword Spotting and Verification”, Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing, Salt Lake City, Utah, vol. 1, pp. 377–380, 2001.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chau, C.K., Lai, C.S., Shi, B.E. (2001). Feature vs. Model Based Vocal Tract Length Normalization for a Speech Recognition-Based Interactive Toy. In: Liu, J., Yuen, P.C., Li, Ch., Ng, J., Ishida, T. (eds) Active Media Technology. AMT 2001. Lecture Notes in Computer Science, vol 2252. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45336-9_17
Download citation
DOI: https://doi.org/10.1007/3-540-45336-9_17
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43035-3
Online ISBN: 978-3-540-45336-9
eBook Packages: Springer Book Archive