Abstract
The performance of current HMM-based automatic speech recognition (ASR) systems degrade significantly in real-world applications where there exist mismatches between training and testing conditions caused by factors such as mismatched signal capturing and transmission channels and additive environmental noises. Among many approaches proposed previously to cope with the above robust ASR problem, two notable HMM compensation approaches are the so-called Parallel Model Combination (PMC) and Vector Taylor Series (VTS) approaches, respectively. In this paper, we introduce a new HMM compensation approach using a technique called Unscented Transformation (UT). As a first step, we have studied three implementations of the UT approach with different computational complexities for noisy speech recognition, and evaluated their performance on Aurora2 connected digits database. The UT approaches achieve significant improvements in recognition accuracy compared to log-normal-approximation-based PMC and first-order-approximation-based VTS approaches.
This work was done while Y. Hu worked at The University of Hong Kong, and was supported by grants from the RGC of the Hong Kong SAR (Project No. HKU 7039/02E) and Anhui USTC iFLYTEK Co. Ltd., Hefei, China.
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
Acero, A., Deng, L., Kristjansson, T., Zhang, J.: HMM adaptation using vector Taylor series for noisy speech recognition. In: Proc. ICSLP, Beijing, pp. 869–872 (2000)
Gales, M.J.F.: Model-based Techniques For Noise Robust Speech Recognition, Ph.D. thesis, Cambridge University, UK (1995)
Hirsch, H.G., Pearce, D.: The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In: Proc. ISCA ITRW ASR, Paris, France, September 2000, pp. 181–188 (2000)
Julier, S.J.: The spherical simplex unscented transformation. In: Proc. Amer. Control Conf., Denver, Colorado, June 2003, pp. 2430–2434 (2003)
Julier, S.J., Uhlmann, J.K.: Unscented filtering and nonlinear estimation. Proceedings of the IEEE 92(3), 401–422 (2004)
Kim, D.-Y., Un, C.-K., Kim, N.-S.: Speech recognition in noisy environments using first-order vector Taylor series. Speech Communication 24, 39–49 (1998)
Moreno, P.J.: Speech Recognition in Noisy Environments, Ph.D. thesis, Carnegie Mellon University (1996)
Moreno, P.J., Raj, B., Stern, R.M.: A vector Taylor series approach for environment-independent speech recognition. In: Proc. ICASSP, Atlanta, pp. 733–736 (1996)
Young, S.J., et al.: The HTK Book (revised for HTK Version 3.3) (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hu, Y., Huo, Q. (2006). An HMM Compensation Approach Using Unscented Transformation for Noisy Speech Recognition. In: Huo, Q., Ma, B., Chng, ES., Li, H. (eds) Chinese Spoken Language Processing. ISCSLP 2006. Lecture Notes in Computer Science(), vol 4274. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11939993_38
Download citation
DOI: https://doi.org/10.1007/11939993_38
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-49665-6
Online ISBN: 978-3-540-49666-3
eBook Packages: Computer ScienceComputer Science (R0)