• DocumentCode
    3585083
  • Title

    A keyword search system using open source software

  • Author

    Trmal, Jan ; Guoguo Chen ; Povey, Dan ; Khudanpur, Sanjeev ; Ghahremani, Pegah ; Xiaohui Zhang ; Manohar, Vimal ; Chunxi Liu ; Jansen, Aren ; Klakow, Dietrich ; Yarowsky, David ; Metze, Florian

  • Author_Institution
    Johns Hopkins Univ., Baltimore, MD, USA
  • fYear
    2014
  • Firstpage
    530
  • Lastpage
    535
  • Abstract
    Provides an overview of a speech-to-text (STT) and keyword search (KWS) system architecture build primarily on the top of the Kaldi toolkit and expands on a few highlights. The system was developed as a part of the research efforts of the Radical team while participating in the IARPA Babel program. Our aim was to develop a general system pipeline which could be easily and rapidly deployed in any language, independently on the language script and phonological and linguistic features of the language.
  • Keywords
    feature extraction; natural languages; speech recognition; speech-based user interfaces; IARPA Babel program; KWS system architecture; Kaldi toolkit; Radical team; STT system architecture; keyword search system; keyword search system architecture; language script; linguistic features; open source software; phonological features; speech-to-text system architecture; Decoding; Keyword search; Lattices; NIST; Speech; Training; Vocabulary; IARPA BABEL; Kaldi; OpenKWS; deep neural networks; keyword search; pitch; speech recognition; spoken term detection;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Spoken Language Technology Workshop (SLT), 2014 IEEE
  • Type

    conf

  • DOI
    10.1109/SLT.2014.7078630
  • Filename
    7078630