Abstract
Mel-frequency cepstral coefficients (MFCC) are the most widely used features in current speech recognition systems. However, they have a poor physical interpretation and they do not lie in the frequency domain. Frequency filtering (FF) is a technique that has been recently developed to design frequency-localized speech features that perform similar to MFCC in terms of recognition performances. Motivated by our desire to build time-frequency speech models, we wanted to use the FF technique as front-end. However, when evaluating FF on the Aurora-3 database we found some discrepancies in the highly mismatch case. This led us to put FF in another perspective: the wavelet transform. By doing so, we were able to explain the discrepancies and to achieve significant improvements in recognition in the highly mismatch case.
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
Nadeu, C.: On the decorrelation of filter-bank energies in speech recognition. In: Eurospeech. (1995)
Nadeu, C., et al: Time and frequency filtering of filter-bank energies for robust HMM speech recognition. Speech Communication 34 (2001) 93–114
Paliwal, K.: Decorrelated and liftered filter-bank energies for robust speech recognition. In: Eurospeech. (1999)
Marsal, P., et al: Comparison and combination of RASTA-PLP and FF features in hybrid HMM/MLP speech recognition system. In: ICSLP. (2002)
Hirsch, H., Pearce, D.: The AURORA experimental framework for the performance evaluation of s.r. systems under noisy conditions. In: ASR2000, Paris, France (2000)
Mallat, S.: A wavelet tour of signal processing. Academic Press (1999)
Macho, D., et al: Evalutaion of noise-robust DSR front-end on AURORA databases. In: ICSLP. (2002)
Nadeu, C.: On the filter-bank parameterization front-end for robust HMM speech recognition. In: Robust Methods for S. R. in Adverse Conditions, Finland (1999)
Gowdy, J., Tufekci, Z.: Mel-scaled discrete wavelet coefficients for speech recognition. In: ICASSP. (2000)
Sarikaya, R., Pellom, B.L., Hansen, J.H.L.: Wavelet packet transform features with application to speaker identification. In: IEEE Nordic Signal Proc. Symp. (1998)
Sarikaya, R., Hansen, J.H.L.: High resolution speech feature extraction parameterization for monophone-based stressed speech recognition. IEEE Signal Processing Letters 7 (2000) 182–185
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Deviren, M., Daoudi, K. (2003). Frequency and Wavelet Filtering for Robust Speech Recognition. In: Kaynak, O., Alpaydin, E., Oja, E., Xu, L. (eds) Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003. ICANN ICONIP 2003 2003. Lecture Notes in Computer Science, vol 2714. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44989-2_54
Download citation
DOI: https://doi.org/10.1007/3-540-44989-2_54
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40408-8
Online ISBN: 978-3-540-44989-8
eBook Packages: Springer Book Archive