Advertisement

Dynamic Time Warping Inside a Genetic Algorithm for Automatic Speech Recognition

  • Fadila Maouche
  • Mohamed Benmohammed
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 64)

Abstract

The technology of the automatic speech recognition is in full grow, a multitude of algorithms have been developed to improve the performance and robustness of ASR (Automatic Speech Recognition) systems. The most studied methods in recent years are those inspired by nature as genetic algorithms. In this article, we will introduce a system that uses a genetic algorithm and dynamic time warping for automatic recognition of isolated Arabic words, tested in noisy environment and in isolated environment.

Keywords

Automatic speech recognition Genetic algorithm Dynamic time warping Arabic language Mel frequency cepstral coefficients (MFCC) Oral corpus 

References

  1. 1.
    Haton, J.-P., Pierrel, J.M., Perennou, G., Callean, J., Gauvain, J.-L.: Automatic speech recognition, Dunod edition (1999)Google Scholar
  2. 2.
  3. 3.
    Robot guidé par reconnaissance vocale, PPE (2004). www.tigen.org/perso/geogeo/TPE_Vocale/Dossier%20(Reconnaissance%20vocale).pdf
  4. 4.
    Ganchev, T.D.: Speaker recognition. Dissertation subject at the Patras University for the Doctor degree of philosophy, Greece (2005)Google Scholar
  5. 5.
    Jacob, B.: Un outil informatique de gestion de modéles de markov caches: expérimentations en reconnaissance de la parole, Ph.D. thesis at the Paul Sabatier University in Toulouse III (1995)Google Scholar
  6. 6.
    Ellis, D.:  « PLP et RASTA (et MFCC, et inversion) dans Matlab employer melfcc.m et invmelfcc.m » (2006). http://www.ee.columbia.edu/~dpwe/resources/matlab/rastamat/
  7. 7.
    Mami, Y.: Reconnaissance de locuteurs par localisation dans un espace de locuteurs de references, doctoral thesis, signal and image speciality, telecommunication national school, Paris (2003)Google Scholar
  8. 8.
    Foukou, A., Henaff, S., Lagacherie, M., Rouget, P.: Final presentation of Marvin project (Modest-encoding AlgoRIthm with Vocal IdentificatioN), EPITA (2002)Google Scholar
  9. 9.
    Hernandez, J.: Algorithmes d’acquisition, compression et restitution de la parole à vitesse variable, étude et mise en place » , graduation project (1995)Google Scholar
  10. 10.
    Moraru, D.: « Segmentation en locuteurs de documents audios et audiovisuels: application à la recherche d’information multimédia » , thesis for doctor degree of inpg, speciality: signal image parole télécoms, national polytechnic institute Grenoble (2004)Google Scholar
  11. 11.
    Mathematic distance, Wikipédia, https://fr.wikipedia.org/wiki/Distance_(math%C3%A9matiques). Accessed 8 Sept 2018
  12. 12.
    Obitko, M.: Genetic algorithms, University of Applied Sciences Dresden (FH) (1998)Google Scholar
  13. 13.
    Melanie, Mitchell: An Introduction to Genetic Algorithms, A Bradford Book the MIT Press, Fifth Printing. Massachusetts, London, England, Cambridge (1999)Google Scholar
  14. 14.
    Dumeur, R.: Synthèse de comportements animaux individuels et collectives par algorithms génétiques, science department, artificial intelligence institute, Paris_8 university (1995)Google Scholar
  15. 15.
    Amédée, S., Francois-Gérard, R.: Genetic algorithms, thesis of the end of the year, Mr Philippe Tutoring Audebaud, supported on 21/06/2004Google Scholar
  16. 16.
    Maouche, F., Benmohammed, M.: Evolutionist approach and MFCC modeling for Arabic automatic recognition. RIST, vol 18 (2010)Google Scholar
  17. 17.
    Néel, F., Chollet, G., Lamel, L., Minker, W.: Reconnaissance et compréhension de la parole: evaluation et applications. The LIMSI and CNRS laboratories in FranceGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Emir Abd El Kader UniversityConstantineAlgeria
  2. 2.Abd El Hamid Mehri UniversityConstantineAlgeria

Personalised recommendations