The AT&T WATSON Speech Recognizer

Vincent Goffin, Cyril Allauzen, Enrico Bocchieri, Dilek Hakkani-Tür, Andrej Ljolje, Sarangarajan Parthasarathy, Mazin G. Rahim, Giuseppe Riccardi, Murat SaraçlarICASSP 2005 · OpenReview

Abstract

This paper describes the AT&T WATSON real-time speech recognizer, the product of several decades of research at AT&T. The recognizer handles a wide range of vocabulary sizes and is based on continuous-density hidden Markov models for acoustic modeling and finite state networks for language modeling. The recognition network is optimized for efficient search. We identify the algorithms used for high-accuracy, real-time and low-latency recognition. We present results for small and large vocabulary tasks taken from the AT&T VoiceTone/sup /spl reg// service, showing word accuracy improvement of about 5% absolute and real-time processing speed-up by a factor between 2 and 3.
BibTeX
@inproceedings{goffin2005at,
  author = {Vincent Goffin and Cyril Allauzen and Enrico Bocchieri and Dilek Hakkani-Tür and Andrej Ljolje and Sarangarajan Parthasarathy and Mazin G. Rahim and Giuseppe Riccardi and Murat Saraçlar},
  title = {{The AT\&T WATSON Speech Recognizer}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2005},
  url = {https://openreview.net/forum?id=9PNRIcpy10},
}

Loading related content...

Figure