• DocumentCode
    2229253
  • Title

    Research on the algorithm of communication network speech enhancement based on BP neural network

  • Author

    Yongjun, Peng ; Huanyu, Xiong ; Xi, Guo ; Hao, Liu ; Jianjin, Zou

  • Author_Institution
    Commun. Command Acad. of PLA, China
  • Volume
    3
  • fYear
    2010
  • fDate
    20-22 Aug. 2010
  • Abstract
    Speech is one of the best natural and convenient intercommunication manners among humankind. Nowadays, speech processing technologies have been broadly used in many applied fields. In this paper, the main research focus is on the study of speech enhancement and separation, which is one of the key technologies when we try to put the speech processing into reality. Firstly, we introduce speech single as well as the neural network elementary theory and propose based on the BP neural network speech enhancement system modeling method. Secondly, we integrate voice feature extraction and summarize the speech cepstrum and noise cepstrum valuation for neural network training and learning in order to eliminate the noise. Finally, the experiment proved this method surpass traditional the speech enhancement algorithm. The simulation result shows that this speech enhancement system design method can save the running time and the effect is good.
  • Keywords
    backpropagation; feature extraction; interference suppression; neural nets; speech enhancement; BP neural network; communication network speech enhancement; neural network elementary theory; neural network training; noise cepstrum; noise elimination; speech cepstrum; speech processing technology; voice feature extraction; Adaptation model; Artificial neural networks; Computational modeling; Convergence; Noise; Noise measurement; algorithm research; cepstrum coefficient; neural network; speech enhancement;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Advanced Computer Theory and Engineering (ICACTE), 2010 3rd International Conference on
  • Conference_Location
    Chengdu
  • ISSN
    2154-7491
  • Print_ISBN
    978-1-4244-6539-2
  • Type

    conf

  • DOI
    10.1109/ICACTE.2010.5579579
  • Filename
    5579579