• DocumentCode
    2984871
  • Title

    Improving Bone-Conducted Speech Quality via Neural Network

  • Author

    Shimamura, Tetsuya ; Mamiya, J. ; Tamiya, Toshiki

  • Author_Institution
    Dept. of Inf. & Comput. Sci., Saitama Univ.
  • fYear
    2006
  • fDate
    Aug. 2006
  • Firstpage
    628
  • Lastpage
    632
  • Abstract
    The quality of bone-conducted speech is low, but bone-conducted speech itself is not affected by noise. In this paper, we take into account such properties of bone-conducted speech, and derive a reconstruction filter to improve the quality of bone-conducted speech. The reconstruction filter is designed by learning a neural network on the basis of the bone-conducted speech and normal speech obtained from a speaker. Experimental results show that the reconstructed speech signal has better quality than the bone-conducted speech signal
  • Keywords
    filtering theory; neural nets; speech processing; bone-conducted speech quality; neural network; reconstruction filter; Bones; Filtering; Filters; Frequency; Neural networks; Signal design; Signal processing; Speech enhancement; Speech processing; Working environment noise; bone conduction; neural network; reconstruction filter; speech quality;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signal Processing and Information Technology, 2006 IEEE International Symposium on
  • Conference_Location
    Vancouver, BC
  • Print_ISBN
    0-7803-9753-3
  • Electronic_ISBN
    0-7803-9754-1
  • Type

    conf

  • DOI
    10.1109/ISSPIT.2006.270876
  • Filename
    4042318
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2984871