An HMM Compensation Approach Using Unscented Transformation for Noisy Speech Recognition
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.
KeywordsSpeech Recognition Automatic Speech Recognition Clean Speech Noisy Speech Automatic Speech Recognition System
Unable to display preview. Download preview PDF.
- 1.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)Google Scholar
- 2.Gales, M.J.F.: Model-based Techniques For Noise Robust Speech Recognition, Ph.D. thesis, Cambridge University, UK (1995)Google Scholar
- 3.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)Google Scholar
- 4.Julier, S.J.: The spherical simplex unscented transformation. In: Proc. Amer. Control Conf., Denver, Colorado, June 2003, pp. 2430–2434 (2003)Google Scholar
- 7.Moreno, P.J.: Speech Recognition in Noisy Environments, Ph.D. thesis, Carnegie Mellon University (1996)Google Scholar
- 8.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)Google Scholar
- 9.Young, S.J., et al.: The HTK Book (revised for HTK Version 3.3) (2005)Google Scholar