Abstract
An analysis based on wavelet modulation scales feature extraction is proposed. Considering human auditory perception and varieties of disturbances, instead of the frequency differences, wavelet modulation scales are adopted to reflect the dynamic features of speech in ASR. Experiments for the Chinese digit-string recognition show extracting the wavelet modulation scales as the dynamic features have good performance both in additional noises and convolutional noises environment.
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
Hermansky, H.: Human Speech Perception: Some Lesson From Automatic Speech Recognition (TSD 2001, Zelezna Ruda, Czech Republic, September 2001 in TSD 2001[DB/OL], Zelezna Ruda)
Rabiner, L.R., Juang, B.H.: Fundementals of Speech Recognition, pp. 194–200. Prentice Hall, Englewood Cliffs (1993)
Boll, S.: Suppression, of acoustic noise in speech using spectral subtraction. IEEE and Signal Processing, 113–120 (April 1979)
Hermansky, H.: The Modulation Spectrum in Automatic Recognition of Speech. In: IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 140–147 (1997)
Kandel, E.R., Schwartz, J.H., Jessell, T.M.: Principles of Neural Science, ch. 32 Hearing, 3rd edn., pp. 481–498. Elsevier Science Publishing, Amsterdam (1991)
Xian-da, Z.: Modern Signal Processing, pp. 456–457. The Tsinghua University press (1995)
Sukittanon, S., Atlas, L.E.: Channel Compensation of Modulation Spectral Features. In: Proceedings of the 2003 IEEE ISCAS (2003)
Sukittanon, S., Atlas, L.E.: Modulation Frequency Features for Audio Fingerprinting. In: Proc. of ICASSP 2002, pp. 1173–1176 (2002)
Arai, T., Pavel, M., Hermansky, H., Avendano, C.: Intelligibility of speech with filtered time trajectories of spectral envelopes. In: Proc. ICSLP 1996, Philadelphia, October 1996, pp. 2490–2493 (1996)
Oppenheim, A.V., Schafer, R.W.: Digital signal Processing, pp. 85–86. Prentice Hall, Englewood Cliffs (1975)
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
Ma, X., Zhou, W., Ju, F., Jiang, Q. (2006). Speech Feature Extraction Based on Wavelet Modulation Scale for Robust Speech Recognition. In: King, I., Wang, J., Chan, LW., Wang, D. (eds) Neural Information Processing. ICONIP 2006. Lecture Notes in Computer Science, vol 4233. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11893257_56
Download citation
DOI: https://doi.org/10.1007/11893257_56
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-46481-5
Online ISBN: 978-3-540-46482-2
eBook Packages: Computer ScienceComputer Science (R0)