Abstract
This paper describes a novel extension to warped minimum variance distortionless response (MVDR) spectral estimation which allows to steer the resolution of the spectral envelope estimation to lower or higher frequencies while keeping the overall resolution of the estimate and the frequency axis fixed. This effect can be achieved by the introduction of a second bilinear transformation to the warped MVDR spectral estimation, but now in the frequency domain as opposed to the first bilinear transformation which is applied in the time domain, and a compensation step to adjust for the pre-emphasis of both bilinear transformations. In the feature extraction process of an automatic speech recognition system this novel extension allows to emphasize classification relevant characteristics while dropping classification irrelevant characteristics of speech features according to the characteristics of the signal to analyze.
We have compared the novel extension to warped MVDR and the traditional Mel frequency cepstral coefficients (MFCC) on development and evaluation data of the Rich Transcription 2005 Spring Meeting Recognition Evaluation lecture meeting task. The results are promising and we are going to use the described warped and warped-twice front-end settings in the upcoming NIST evaluation.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
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
Malayath, N.: Data-driven methods for extracting features from speech. Ph.D. dissertation, Oregon Graduate Institute of Science and Technology (January 2000)
Wölfel, M., McDonough, J.: Minimum variance distortionless response spectral estimation, review and refinements. IEEE Signal Processing Magazine 22(5), 117–126 (2005)
Murthi, M., Rao, B.: All-pole model parameter estimation for voiced speech. In: IEEE Workshop Speech Coding Telecommunications Proc., Pacono Manor, PA (1997)
Murthi, M., Rao, B.: All-pole modeling of speech based on the minimum variance distortionless response spectrum. IEEE Trans. Speech Audio Processing 8(3), 221–239 (2000)
Dharanipragada, S., Rao, B.: MVDR based feature extraction for robust speech recognition. In: Proc. ICASSP, vol. 1, pp. 309–312 (2001)
Wölfel, M., McDonough, J., Waibel, A.: Minimum variance distortionless response on a warped frequency scale. In: Proc. Eurospeech, pp. 1021–1024 (2003)
Nakatoh, Y., Nishizaki, M., Yoshizawa, S., Yamada, M.: An adaptive Mel-LP analysis for speech recognition. In: Proc. ICSLP (2004)
Musicus, B.: Fast MLM power spectrum estimation from uniformly spaced correlations. IEEE Trans. Acoustics, Speech, Signal Processing 33, 1333–1335 (1985)
Matsumoto, H., Moroto, M.: Evaluation of Mel-LPC cepstrum in a large vocabulary continuous speech recognition. In: Proc. ICASSP, vol. 1, pp. 117–120 (2001)
Oppenheim, A.V., Schafer, R.W.: Discrete-time signal processing. Prentice-Hall Inc., Englewood Cliffs (1989)
National Institute of Standards and Technology (NIST), Rich transcription 2005 spring meeting recognition evaluation (June 2005), http://www.nist.gov/speech/tests/rt/rt2005/spring
Linguistic Data Consortium (LDC), Translanguage english database, LDC2002S04
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
Wölfel, M. (2006). Warped and Warped-Twice MVDR Spectral Estimation With and Without Filterbanks. In: Renals, S., Bengio, S., Fiscus, J.G. (eds) Machine Learning for Multimodal Interaction. MLMI 2006. Lecture Notes in Computer Science, vol 4299. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11965152_24
Download citation
DOI: https://doi.org/10.1007/11965152_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69267-6
Online ISBN: 978-3-540-69268-3
eBook Packages: Computer ScienceComputer Science (R0)