Abstract
This paper presents a hybrid technique combining the Karhonen-Loeve Transform (KLT), the Multilayer Perceptron (MLP) and Genetic Algorithms (GAs) to obtain less-variant Mel-frequency parameters. The advantages of such an approach are that the robustness can be reached without modifying the recognition system, and that neither assumption nor estimation of the noise are required. To evaluate the effectiveness of the proposed approach, an extensive set of continuous speech recognition experiments are carried out by using the NTIMIT telephone speech database. The results show that the proposed approach outperforms the baseline and conventional systems.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Ephraim, Y., Van Trees, H.L.: A signal subspace approach for Speech Enhancement. IEEE Transactions on Speech and Audio Processing 3(4), 251–266 (1995)
Fisher, W.M., Dodington, G.R., Goudie-Marshall, K.M.: The DARPA Speech Recognition Research Database: Specification and Status. In: Proc. DARPA Workshop on Speech Recognition, pp. 93–99 (1986)
Gaylor, W.D.: Telephone voice transmission. standards and measurements. Prentice Hall, Englewood Cliffs (1989)
Goldberg, D.E.: Genetic algorithms in search, optimization and machine learning. Addison-Wesley Publishing, Reading (1989)
Gong, Y.: Speech Recognition in Noisy Environments: A survey. Speech Communication 16, 261–291 (1995)
Haverinen, H., Salmela, P., Hakkinen, J., Lehtokangas, M., Saarinen, J.: MLP Network for Enhancement of Noisy MFCC Vectors. In: Proc. Eurospeech, pp. 2371–2374 (1999)
Houk, C.R., Joines, J.A., Kay, M.G.: A Genetic Algorithm for function optimization: a matlab implementation, North Carolina University-NCSU-IE, TR 95-09 (1995)
Jankowski, C., Kalyanswamy, A., Basson, S., Spitz, J.: NTIMIT: A phonetically balanced continuous speech, telephone bandwidth speech database. In: Proc. IEEE-ICASSP, vol. 1, pp. 109–112 (1990)
Moreno, P.J., Stern, R.: Sources of degradation of speech recognition in the telephone network. In: Proc. IEEE-ICASSP, vol. 1, pp. 109–112 (1994)
Selouani, S.-A., O’Shaughnessy, D.: Robustness of speech recognition using genetic algorithms and a Mel-cepstral subspace approach. Proc. IEEE-ICASSP I, 201–204 (2004)
Selouani, S.-A., O’Shaughnessy, D.: Investigation into a Mel Subspace Based Front-End Processing for Robust Speech Recognition. In: Proc. IEEE-International symposium in signal processing and Information Technology, Roma, pp. 187–190 (2004)
Speech Group, Cambridge University, The HTK Book (Version 3.4), Cambridge University Group (2006)
Weintraub, M., Beaufays, F.: Increased Robustness of Noisy Speech Features Using Neural Networks. In: Workshop on Robust Methods for Speech Recognition in Adverse Conditions, Tampere, Finland (May 1999)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Selouani, SA., Hamam, H., O’Shaughnessy, D. (2007). A Hybrid Genetic-Neural Front-End Extension for Robust Speech Recognition over Telephone Lines. In: Chetouani, M., Hussain, A., Gas, B., Milgram, M., Zarader, JL. (eds) Advances in Nonlinear Speech Processing. NOLISP 2007. Lecture Notes in Computer Science(), vol 4885. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-77347-4_14
Download citation
DOI: https://doi.org/10.1007/978-3-540-77347-4_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-77346-7
Online ISBN: 978-3-540-77347-4
eBook Packages: Computer ScienceComputer Science (R0)