Abstract
The automatic speech recognition is an area of active study since the early 1950s, and the latest technologies in the field of stochastic processes and the discovery of Hidden Markov Models have given a new direction for this area.
This paper describes an approach of speech recognition by using the Mel-Scale Frequency Cepstral Coefficients (MFCC) from speech recognition experiments done on OLLO French corpus by different features. Our work consists in finding the most appropriate choice for this task using the Mel-Scale Frequency Cepstral Coefficients (MFCC) extracted from speech signal.
To evaluate this analysis, we built an ASR reference system based on the modeling of phonemes by the HMM (Hidden Markov Models) associated with the GMM models (Gaussian Mixture Model) using the HTK tool. The implementation of this system was made using several experiments in order to choose the best parameters used in two main steps to build an ASR system, acoustic analysis and decoding. The experiments show that the choice of 25 Gaussian components provides a good compromise between recognition accuracy and computation time, and we found also that the best parameters leading to good recognition accuracy are MFCC_E_D_A coefficients with 92.5%.
In this paper the quality and testing of speaker recognition and gender recognition system is completed and analysed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Haton, J.-P.: Reconnaissance Automatique de la Parole. Paris (2006)
Patel, K., Prasad, R.K.: Speech recognition and verification using MFCC & VQ. Int. J. Emerg. Sci. Eng. (IJESE) 1(7) (2013). ISSN: 2319–6378
Huang, L., Zhang, X.: Speaker independent recognition on OLLO French corpus by using different features. In: 2010 First International Conference on Pervasive Computing, Signal Processing and Applications
Modic, R.: Comparative wavelet and MFCC speech recognition experiments on the Slovenian and English SpeechDat2
Nguyen, Q.C.: Reconnaissance de la Parole en Langue Vietnamienne. thèse de doctorat, Institut national polytechnique de Grenoble, Juin 2002
Bakis, R.: Continuous speech recognition via centisecond acoustic states, 91th. Meeting of the Acoust.Soc, avril 1976
Young, S., et al.: The HTK Book (for HTK Version 3.4), p. 198 (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Youcef, B.C., Elemine, Y.M., Islam, B., Farid, B. (2017). Speech Recognition System Based on OLLO French Corpus by Using MFCCs. In: Chadli, M., Bououden, S., Zelinka, I. (eds) Recent Advances in Electrical Engineering and Control Applications. ICEECA 2016. Lecture Notes in Electrical Engineering, vol 411. Springer, Cham. https://doi.org/10.1007/978-3-319-48929-2_25
Download citation
DOI: https://doi.org/10.1007/978-3-319-48929-2_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-48928-5
Online ISBN: 978-3-319-48929-2
eBook Packages: EngineeringEngineering (R0)