ISCA Archive Interspeech 2012
ISCA Archive Interspeech 2012

Discriminative training using non-uniform criteria for keyword spotting on spontaneous speech

Chao Weng, Biing-Hwang (Fred) Juang, Daniel Povey

In this work, we investigate the feasibility of applying our prior works on discriminative training (DT) using non-uniform criteria to a keyword spotting task on spontaneous conversational speech. One of DT methods, minimum classification error (MCE), is recast and efficiently implemented in the weighted finite state transducer (WFST) framework to fit a keyword spotting task. To validate our approach, we evaluate it on a conversational speech task, the credit card use subset of Switchboard, in both kinds of keyword spotting scenarios: one is when a large vocabulary continuous speech recognition (LVCSR) decoder is available, the other is when a simple word-loop grammar of limited vocabulary is used. The results show our approach performs well in both cases, achieving 2.77% and 3.15% figure of merits (FOMs) absolute improvements

Index Terms: LVCSR, keyword spotting, DT, non-uniform criteria, WFST


doi: 10.21437/Interspeech.2012-172

Cite as: Weng, C., Juang, B.-H., Povey, D. (2012) Discriminative training using non-uniform criteria for keyword spotting on spontaneous speech. Proc. Interspeech 2012, 559-562, doi: 10.21437/Interspeech.2012-172

@inproceedings{weng12_interspeech,
  author={Chao Weng and Biing-Hwang (Fred) Juang and Daniel Povey},
  title={{Discriminative training using non-uniform criteria for keyword spotting on spontaneous speech}},
  year=2012,
  booktitle={Proc. Interspeech 2012},
  pages={559--562},
  doi={10.21437/Interspeech.2012-172},
  issn={2958-1796}
}