@Article{ Azzopardi/Semnani_et_al:1998,
  author=       { Daniel Azzopardi, and Shahram Semnani, and Ben Milner, and 
                  Richard Wiseman },
  year  =       { 1998 },
  institution=  { BT Labs (U.K.) }
  title =       { Improving Accuracy of Telephony-based, Speaker-Independent 
                  Speech Recognition },
  number =      { 543 },
  journal=      { ICSLP'98 Proceedings },
  annote=       {

   A combination of techniques for increasing recognition accuracy has
   been developed for an automated corporate directory system with
   120,000 entries. Using a traditional recogniser an accuracy of around
   60% has previously been obtained for both a 156 town name task and
   1108 road name task. Techniques presented in this paper comprise
   front-end modifications, context dependent models, improved lexicon
   and noise modelling. This resulted in an increased recognition accuracy
   of around 90%. 

    - G.Pradeep/S.Gupta (02/2000)}
}


@Article{Dutoit/Shroeter:1998,
  author=       { Thierry Dutoit, Juergen Shroeter },
  year  =       { 1998},
  institution=  { FPM (Belgium), AT&T Labs - Research (USA) }
  title =       { Plug and Play Software for Designing High-Level Speech
                  Processing Systems },
  number =      { 520 },
  month =       { },
  annote=       {

    Software engineering for research and development in the area of signal
    processing is by no means unimportant. For speech processing, in
    particular, it should be a priority: given the intrinsic complexity of
    text-to-speech or recognition systems, there is little hope to do
    state-of-the-art research without solid and extensible code. This paper
    describes a simple and efficient methodology for the design of maximally
    reusable and extensible software components for speech and signal
    processing. The resulting programming paradigm allows software
    components to be advantageously combined with each other in a way that
    recalls the concept of hardware plug-and-play, without the need for
    incorporating complex schedulers to control data flows. It has been
    successfully used for the design of a software library for high-level speech
    processing systems at AT&T Labs, as well as for several other large-scale
    software projects. 

    - G.Pradeep/S.Gupta (02/2000)}
}

@Article{ Hoshimi/Yamada_et_al:1998,
  author=       { Masakatsu Hoshimi, and Maki Yamada, and Katsuyuki Niyada, and 
                  Shozo Makino },
  year  =       { 1998 },
  institution=  { MRIT (Japan), MRIT (Japan), CRL-MEICL(Japan), TU (Japan) }
  title =       { A Study of Noise Robustness for Speaker Independent Speech 
                  Recognition Method Using Phoneme Similarity Vector },
  number =      { 257 },
  journal=      { ICSLP'98 Proceedings },
  annote=       {

    As an input method for rapidly spreading small portable information
    devices, development of speaker independent speech recognition
    technology which can be embedded on a single DSP is now urgently
    requested. We have reported a speech recognition method using phoneme
    similarity vector as a feature vector, which is quite robust for reduction of
    precision of the feature parameter. We've also developed a recognition
    board with a single DSP, which works 100-word vocabulary using only
    the internal memory inside the DSP. [1][2] In this report, we propose a
    new technique which makes our recognition method more robust, where
    a newly introduced noise standard template together with traditional
    phoneme standard templates for calculating phoneme similarity vector
    realizes precise word-spotting. When the newly proposed noise robustness
    method was tested with 100 isolated word vocabulary speech of 50
    subjects, recognition accuracy of 94.7% was obtained under various noisy
    environments. 
    
    - G.Pradeep/S.Gupta (02/2000)}
}