Abstract
In this paper, a novel pitch mean based frequency warping (PMFW) method is proposed to reduce the pitch variability in speech signals at the front-end of speech recognition. The warp factors used in this process are calculated based on the average pitch of a speech segment. Two functions to describe the relations between the frequency warping factor and the pitch mean are defined and compared. We use a simple method to perform frequency warping in the Mel-filter bank frequencies based on different warping factors. To solve the problem of mismatch in bandwidth between the original and the warped spectra, the Mel-filters selection strategy is proposed. At last, the PMFW mel-frequency cepstral coefficient (MFCC) is extracted based on the regular MFCC with several modifications. Experimental results show that the new PMFW MFCCs are more distinctive than the regular MFCCs.
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
Huang, X.D., Acero, A., Hon, H.W.: Spoken Language Processing: A Guide to Theory, Algorithm, and System Development. Prentice Hall, New Jersey (2001)
Lee, L., Rose, R.C.: Speaker Normalization Using Effiecient Frequency Warping Procedures. In: Proc. ICASSP, pp. 353–356 (1996)
Pitz, M., Ney, H.: Vocal Tract Normalization as Linear Transformation of MFCC. In: Proc. EUROSPEECH, pp. 1445–1448 (2003)
Wang, W., Zahorian, S.A.: Vocal Tract Normalization Based on Spectral Warping. In: Proc. ICSLP, pp. 1185–1188 (2004)
Faria, A., Gelbart, D.: Efficient Pitch-based Estimation of VTLN Warp Factors. In: Proc. INTERSPEECH, pp. 213–216 (2005)
Laroche, J., Dolson, M.: New Phase-Vocoder Techniques for Pitch-Shifting, Harmonizing and Other Exotic Effects. In: Proc. 1999 IEEE Workshop on Applications of Signal Processing to Audio and Acoustic, pp. 91–94 (1999)
Gouva, E.B., Stern, R.M.: Speaker Normalization through Formant-based Warping of The Frequency Scale. In: Proc. EUROSPEECH, pp. 1139–1142 (1997)
Zhan, P., Westphal, M.: Speaker Normalization Based on Frequency Warping. In: Proc. ICASSP, pp. 1039–1042 (1997)
Magimai-Doss, M., Stephenson, T.A., Bourlard, H.: Using Pitch Frequency Information in Speech Recognition. In: Proc. EUROSPEECH, pp. 2525–2528 (2003)
Zilca, R.D., Kingsbury, B., et al.: Pseudo Pitch Synchronous Analysis of Speech with Applications to Speaker Recognition. IEEE Transactions on Audio, Speech, and Language Processing 14(2), 467–478 (2006)
Glavitsch, U.: Speaker normalization with respect to F0: a perceptual approach, TIKReport Nr. 185 (2005)
Liu, J., Zheng, T.F., et al.: Real-time Pitch Tracking Based on Combined SMDSF. In: Proc. INTERSPEECH, pp. 301–304 (2005)
Wang, D., Zhu, X.Y., Liu, Y.: Multi-Layer Channel Normalization for Frequency-Dynamic Feature Extraction. Journal of Software 12(9), 1523–1529 (2005)
Young, S., et al.: The HTK book (for HTK version 3.2). Cambridge University Engineering Department (2002)
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
Liu, J., Zheng, T.F., Wu, W. (2006). Pitch Mean Based Frequency Warping. 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_13
Download citation
DOI: https://doi.org/10.1007/11939993_13
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)