Recognition of Noisy Words Using the Time Delay Neural Networks Approach

Authors: Khenfer-Koummich Fatima, Mesbahi Larbi, Hendel Fatiha

Abstract:

This paper presents a recognition system for isolated words like robot commands. It’s carried out by Time Delay Neural Networks; TDNN. To teleoperate a robot for specific tasks as turn, close, etc… In industrial environment and taking into account the noise coming from the machine. The choice of TDNN is based on its generalization in terms of accuracy, in more it acts as a filter that allows the passage of certain desirable frequency characteristics of speech; the goal is to determine the parameters of this filter for making an adaptable system to the variability of speech signal and to noise especially, for this the back propagation technique was used in learning phase. The approach was applied on commands pronounced in two languages separately: The French and Arabic. The results for two test bases of 300 spoken words for each one are 87%, 97.6% in neutral environment and 77.67%, 92.67% when the white Gaussian noisy was added with a SNR of 35 dB.

Keywords: Neural networks, Noise, Speech Recognition.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1094779

References:

[1] Barkana, D.E., Das J., Wang F., Groomes T. E., Sarkar N. "Incorporating verbal feedback into a robot-assisted rehabilitation system”. Robotica, 2010.
[2] Courreges F., Edlie A., Poisson G., Vieyres P.” Ergonomic mousse based interface for 3d orientation control of a tele-sonography robot”. In Proceedings of the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2009), St. Louis, USA, PP.61-66, 2009.
[3] Drygajlo A., Prodanov P. J., Ramel G., Meisser M., Siegwart R.” On developing a voice-enabled interface for interactive tour-guide robots”. Advanced Robotics 17, 599-616, 2007.
[4] Elfes A. "Sonar-based real-world mapping and navigation.” IEEE Journal of Robotics and Automation 3, 249-265, 1987.
[5] Ferre M., Macias-guarasa, J.,Aracil R., Barrientos A.” Voice command generator for teleoperated robot systems.” In Proceedings of the IEEE ROMAN 1998, Takamatsu, Japan 1998.
[6] Ben fredj I. and Ouni K. "Optimization of Features Parameters for HMM Phoneme Recognition of TIMIT Corpus”. International Conference on Control, Engineering & Information Technology (CEIT’13). Vol.2, pp.90-94, 2013.
[7] L. R. Rabiner. "A Tutorial on Hidden Markov Models and selected applications in speech recognition”, Proceedings of IEEE, Vol. 77, N°2, pp: 257-286, 1989.
[8] WouterGevaert, GeorgiTsenov, ValeriMladenov, Senior Member, IEEE. "Neural Networks used for Speech Recognition”. Journal of automatic control, university of Belgrade, vol. 20:1-7, 2010.
[9] A. Waibel "Modular construction of time delay neural networks for speech recognition, neural computation”, Vol1, pp. 39-46, MassachusettsUSA, 1989.
[10] Kevin J. Lang, A. Waibel. "A Time Delay Neural Network Architecture for Isolated Word Recognition”; Neural Networks, Vol. 3, pp. 23-43, 1990.
[11] Masahide Sugiyamat, HidehumiSazoait and Alexander H. Waibel. "Review of TDNNs (time delay neural network) architectures for speech recognition”, in Japanese, 1991.
[12] Bennani Y. « Approches Connexionnistes pour la Reconnaissance Automatique du Locuteur » : Modélisation et Identification, Thèse de Doctorat en Sciences, ORSAY, 1992 (in french).
[13] Pierre J. « Techniques neuronales et applications », Les débuts de l'intelligence. 1935 (in french).
[14] http://sourceforge.net/projects/wavesurfer/files/latest/download.
[15] S. Young and al. "The HTK Book (for HTK version 3.4)”. Cambridge University Engineering Department, December 2006. http://htk.eng.cam.ac.uk.