A New Digital Solution Helps Automatic Voice Recognition

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    This scientific work concerning an examination on automatic speech recognition (ASR) frameworks connected with the home automation and to express the importance of this academic work, an itemized investigation of the engineering of speech recognition frameworks was completed. Our goal in Information Systems Engineering Research Group ofAbdelmalekEssaadi University is to choose a speech recognition programming that must work in remote speech conditions and in a rowdy area.

    The proposed framework is using atoolbox called Kaldi, which must correspond as aclient created by an advanced programming language, with any home automation framework.


  • Keywords

    Speech recognition, acoustic model, language model, HMM, n-gram, domotics,Kaldi.

  • References

      [1] Allauzen et J.-L. Gauvain, «Construction automatique du vocabulaire d’un système de transcription,» Journ{'e}es d’Etude sur la Parole, 2004.

      [2] M. Vacher, «Analyse sonore et multimodale dans le domaine de l'assistance à domicile,» 2011.

      [3] R. Dufour, «Transcription automatique de la parole spontanée,» 2010.

      [4] M. Bouallegue, «L’analyse factorielle pour la modélisation acoustique des systèmes de reconnaissance de la parole,» 2013.

      [5] Z. Le-Qing, «Insect sound recognition based on mfcc and pnn,» chez Multimedia and Signal Processing (CMSP), 2011 International Conference on, 2011.

      [6] F. Bougares, «Attelage de systèmes de transcription automatique de la parole,» 2012.

      [7] P. Karanasou, «Phonemic variability and confusability in pronunciation modeling for automatic speech recognition,» 2013.

      [8] N.-T. Le, C. Servan, B. Lecouteux et L. Besacier, «Better Evaluation of ASR in Speech Translation Context Using Word Embeddings,» chez Interspeech 2016, 2016.

      [9] F. Aman, M. Vacher, F. Portet, W. Duclot et B. Lecouteux, «CirdoX: an On/Off-line Multisource Speech and Sound Analysis Software,» chez Language Resources and Evaluation Conference, 2016.

      [10] S. Madikeri, S. Dey, P. Motlicek et M. Ferras, «Implementation of the standard i-vector system for the kaldi speech recognition toolkit,» 2016.

      [11] Gaida, P. Lange, R. Petrick, P. Proba, A. Malatawy et D. Suendermann-Oeft, «Comparing open-source speech recognition toolkits,» Tech. Rep., DHBW Stuttgart, 2014.

      [12] Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel, M. Hannemann, P. Motlicek, Y. Qian, P. Schwarz et others, «The Kaldi speech recognition toolkit,» chez IEEE 2011 workshop on automatic speech recognition and understanding, 2011.

      [13] Povey, M. Hannemann, G. Boulianne, L. Burget, A. Ghoshal, M. Janda, M. Karafi{'a}t, S. Kombrink, P. Motl{'i}{v{c}}ek, Y. Qian et others, «Generating exact lattices in the WFST framework,» chez Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on, 2012.

      [14] C. Allauzen, M. Riley, J. Schalkwyk, W. Skut et M. Mohri, «OpenFst: A general and efficient weighted finite-state transducer library,» chez International Conference on Implementation and Application of Automata, 2007.

      [15] O. Passalacqua, E. Benoit, M.-P. Huget et P. Moreaux, «Integrating OPC Data into GSN Infrastructures,» arXiv preprint arXiv:0808.0055, 2008.

      [16] H. N. Li Zheng, «OPC (OLE for process control) specification and its developments,» 2002.

      [17] Topalis, G. Orphanos, S. Koubias et G. Papadopoulos, «A generic network management architecture targeted to support home automation networks and home internet connectivity,» chez Consumer Electronics, 1999. ICCE. International Conference on, 1999.




Article ID: 16769
DOI: 10.14419/ijet.v7i3.4.16769

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.