Abstract
A method to improve the robustness of the Jacobian adaptation (JA) is proposed. Although it is a usual idea that the reference hidden Markov model (HMM) in the JA is constructed by using the model composition methods like the parallel model combination (PMC), we propose to train the reference HMM directly with the noisy speech and then select the appropriate reference HMM based on the noise types and signal to noise ratio (SNR) values obtained from the input noisy speech. For the estimation of Jacobian matrices and other statistical information for the JA, a data driven method is employed during the training.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
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 (1995)
Moreno, P.J.: Speech Recognition in Noisy Environments. Ph.D. Dissertation. Carnegie Mellon University (1996)
Martin, F.: Recognition of Noisy Speech by Using the Composition of Hidden Markov Models. In: Proc. 1992 Autumn ASJ Conf. (1992)
Sagayama, S., Yamaguchi, Y., Takahashi, S.: Jacobian adaptation of noisy speech models. In: IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 396–403 (1997)
Hung, J.-W., Shen, J.-L., Lee, L.-S.: New approaches for domain transformation and parameter combination for improved accuracy in parallel model combination (PMC) techniques. IEEE Trans. Speech and Audio Processing 9(8), 842–855 (2001)
Rabiner, R.L., Juang, B.-H.: Fundamentals of Speech Recognition. Prentice-Hall, Englewood Cliffs (1993)
Chung, Y.J.: A Data-driven Model Parameter Compensation Method for Noise-Robust Speech Recognition. IEICE Trans. Info. & Syst. E-88-D(3), 432–434 (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jung, Y. (2008). Improving Robustness in Jacobian Adaptation for Noisy Speech Recognition. In: André, E., Dybkjær, L., Minker, W., Neumann, H., Pieraccini, R., Weber, M. (eds) Perception in Multimodal Dialogue Systems. PIT 2008. Lecture Notes in Computer Science(), vol 5078. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69369-7_19
Download citation
DOI: https://doi.org/10.1007/978-3-540-69369-7_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69368-0
Online ISBN: 978-3-540-69369-7
eBook Packages: Computer ScienceComputer Science (R0)