Abstract
Speaker normalization techniques are widely used to improve the accuracy of speaker independent speech recognition. One of the most popular group of such methods is Vocal Tract Length Normalization (VTLN). These methods try to reduce the inter-speaker variability by transforming the input feature vectors into a more compact domain, to achieve better separations between the phonetic classes. Among others, two algorithms are commonly applied: the Maximum Likelihood criterion-based, and the Linear Discriminant criterion-based normalization algorithms. Here we propose the use of the Springy Discriminant criterion for the normalization task. In addition we propose a method for the VTLN parameter determination that is based on pitch estimation. In the experiments this proves to be an efficient and swift way to initialize the normalization parameters for training, and to estimate them for the voice samples of new test speakers.
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
Eide, E., Gish, H.: A parametric approach to vocal tract length normalization. In: Proc. of ICASSP, Munich, pp. 1039–1042 (1997)
Wegmann, S., McAllaster, D., Orloff, J., Peskin, B.: Speaker normalization on coversational telephone speech. In: Proc. of ICASSP, pp. 339–341 (1996)
Acero, A.: Acoustical and environmental robustness in automatic speech recognition. Kluwer Academic Publishers, Dordrecht (1993)
Saon, G., Padmanabhan, M., Gopinath, R.A.: Eliminating inter-speaker variability prior to linear discriminant transforms. In: Proc. of ASRU (2001)
Westphal, M., Schultz, T., Waibel, A.: Linear discriminant – a new criterion for speaker normalization. In: Proc. ICSLP 1998, Morgan Kaufmann Publishers, San Francisco (1998)
Kocsor, A., Kovács, K.: Kernel springy discriminant analysis and its application to a phonological awareness teaching system. In: Sojka, P., Kopeček, I., Pala, K. (eds.) TSD 2002. LNCS (LNAI), vol. 2448, pp. 325–328. Springer, Heidelberg (2002)
Kocsor, A., Tóth, L.: Application of kernel-based feature space transformations and learning methods to phoneme classification. Applied Intelligence 21, 129–142 (2004)
Bánhalmi, A., Kocsor, A., Kovács, K., Tóth, L.: Fundamental frequency estimation by combinations of various methods. In: Proc. of 7th Nordic Signal Processing Symposium (NORSIG) (2006)
Bánhalmi, A., Paczolay, D., Tóth, L., Kocsor, A.: First results of a Hungarian medical dictation project. In: Proc. of IS-LTC, pp. 23–26. Morgan Kaufmann Publishers, San Francisco (2006)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Paczolay, D., Bánhalmi, A., Kocsor, A. (2007). Speaker Normalization Via Springy Discriminant Analysis and Pitch Estimation. In: Matoušek, V., Mautner, P. (eds) Text, Speech and Dialogue. TSD 2007. Lecture Notes in Computer Science(), vol 4629. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74628-7_33
Download citation
DOI: https://doi.org/10.1007/978-3-540-74628-7_33
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74627-0
Online ISBN: 978-3-540-74628-7
eBook Packages: Computer ScienceComputer Science (R0)