• DocumentCode
    294521
  • Title

    Performance of the IBM large vocabulary continuous speech recognition system on the ARPA Wall Street Journal task

  • Author

    Bahl, L.R. ; Balakrishnan-Aiyer, S. ; Bellgarda, J.R. ; Franz, M. ; Gopalakrishnan, P.S. ; Nahamoo, D. ; Novak, M. ; Padmanabhan, M. ; Picheny, M.A. ; Roukos, S.

  • Author_Institution
    IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
  • Volume
    1
  • fYear
    1995
  • fDate
    9-12 May 1995
  • Firstpage
    41
  • Abstract
    In this paper we discuss various experimental results using our continuous speech recognition system on the Wall Street Journal task. Experiments with different feature extraction methods, varying amounts and type of training data, and different vocabulary sizes are reported
  • Keywords
    acoustic signal processing; feature extraction; speech recognition; ARPA Wall Street Journal; IBM large vocabulary continuous speech recognition system; feature extraction methods; performance; training data; vocabulary sizes; Data mining; Feature extraction; Microphones; Spatial databases; Speech recognition; Splicing; Testing; Training data; Vectors; Vocabulary;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on
  • Conference_Location
    Detroit, MI
  • ISSN
    1520-6149
  • Print_ISBN
    0-7803-2431-5
  • Type

    conf

  • DOI
    10.1109/ICASSP.1995.479268
  • Filename
    479268
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=294521