• DocumentCode
    381282
  • Title

    Transducer composition for "on-the-fly" lexicon and language model integration

  • Author

    Caseiro, Diamantino ; Trancoso, Isabel

  • Author_Institution
    L2F Spoken Language Syst. Lab., INESC-ID/IST, Lisbon, Portugal
  • fYear
    2001
  • fDate
    2001
  • Firstpage
    393
  • Lastpage
    396
  • Abstract
    We present the use of a specialized composition algorithm that allows the generation of a determinized search network for ASR in a single step. The algorithm is exact in the sense that the result is determinized when the lexicon and the language model are represented as determinized transducers. The composition and determinization are performed simultaneously, which is of great importance for "on-the-fly" operation. The algorithm pushes the language model weights towards the initial state of the network. Our results show that it is advantageous to use the maximum amount of information as early as possible in the decoding procedure.
  • Keywords
    decoding; deterministic algorithms; linguistics; natural languages; speech recognition; tree searching; vocabulary; ASR; automatic speech recognition; decoding procedure; determinized search network; determinized transducers; language model; lexicon; transducer composition; Automatic speech recognition; Decoding; Interleaved codes; Natural languages; Transducers;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Automatic Speech Recognition and Understanding, 2001. ASRU '01. IEEE Workshop on
  • Print_ISBN
    0-7803-7343-X
  • Type

    conf

  • DOI
    10.1109/ASRU.2001.1034667
  • Filename
    1034667