An optimized multi-duration HMM for spontaneous speech recognition

@inproceedings{Ohkawa2003AnOM,
  title={An optimized multi-duration HMM for spontaneous speech recognition},
  author={Yuichi Ohkawa and Akihiro Yoshida and Motoyuki Suzuki and Akinori Ito and Shozo Makino},
  booktitle={INTERSPEECH},
  year={2003}
}
In spontaneous speech, various speech style and speed changes can be observed, which are known to degrade speech recognition accuracy. In this paper, we describe an optimized multi-duration HMM (OMD). An OMD is a kind of multi-path HMM with at most two parallel paths. Each path is trained using speech samples with short or long phoneme duration. The thresholds to divide samples of phonemes are determined through phoneme recognition experiment. Not only the thresholds but also topologies of HMM… CONTINUE READING