Abstract
We propose a data-driven approach for the Jacobian adaptation (JA) to make it more robust against the noisy environments in speech recognition. The reference hidden Markov model (HMM) in the JA is trained directly with the noisy speech for improved acoustic modeling instead of using the model composition methods like the parallel model combination (PMC). This is made possible by estimating the Jacobian matrices and other statistical information for the adaptation using the Baum-Welch algorithm during the training. The adaptation algorithm has shown to give improved robustness especially when used in a multi-model structure. From the speech recognition experiments based on HMMs, we could find the proposed adaptation method gives better recognition results compared with conventional HMM parameter compensation methods and the multi-model approach could be a viable solution in the noisy speech recognition.
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
Gales, M.J.F.: Model Based Techniques for Noise-Robust Speech Recognition, Ph.D. Dissertation. University of Cambridge, Cambridge (1995)
Moreno, P.J.: Speech Recognition in Noisy Environments, Ph.D. Dissertation, Carnegie Mellon University (1996)
Sagayama, S., Yamaguchi, Y., Takahashi, S.: Jacobian Adaptation of Noisy Speech models. In: IEEE Workshop on Automatic Speech Recognition and Understanding, December 14-17, 1997, pp. 396–403 (1997)
Xu, H., Tan, Z.-H., Dalsgaard, P., Lindberg, B.: Robust Speech Recognition on Noise and SNR Classification – a Multiple-Model Framework. In: Interspeech, Lisbon, Portugal (2005)
Pearce, D., Hirsch, H.-G.: The AURORA Experimental Framework for the performance evaluation of speech recognition systems under noisy conditions. In: ICSLP 2000, Beijing, China (2000)
Baum, L.E., Petrie, G.S.T., Weiss, N.: A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains. Ann. Math. Statist. 41, 164–171 (1970)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Chung, YJ., Bae, KS. (2007). Data-Driven Jacobian Adaptation in a Multi-model Structure for Noisy Speech Recognition. In: Martí, J., Benedí, J.M., Mendonça, A.M., Serrat, J. (eds) Pattern Recognition and Image Analysis. IbPRIA 2007. Lecture Notes in Computer Science, vol 4478. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-72849-8_57
Download citation
DOI: https://doi.org/10.1007/978-3-540-72849-8_57
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-72848-1
Online ISBN: 978-3-540-72849-8
eBook Packages: Computer ScienceComputer Science (R0)