ISCA Archive Interspeech 2005
ISCA Archive Interspeech 2005

Hidden conditional random fields for phone classification

Asela Gunawardana, Milind Mahajan, Alex Acero, John C. Platt

In this paper, we show the novel application of hidden conditional random fields (HCRFs) - conditional random fields with hidden state sequences - for modeling speech. Hidden state sequences are critical for modeling the non-stationarity of speech signals. We show that HCRFs can easily be trained using the simple direct optimization technique of stochastic gradient descent. We present the results on the TIMIT phone classification task and show that HCRFs outperforms comparable ML and CML/MMI trained HMMs. In fact, HCRF results on this task are the best single classifier results known to us. We note that the HCRF framework is easily extensible to recognition since it is a state and label sequence modeling technique. We also note that HCRFs have the ability to handle complex features without any change in training procedure.

doi: 10.21437/Interspeech.2005-126

Cite as: Gunawardana, A., Mahajan, M., Acero, A., Platt, J.C. (2005) Hidden conditional random fields for phone classification. Proc. Interspeech 2005, 1117-1120, doi: 10.21437/Interspeech.2005-126

  author={Asela Gunawardana and Milind Mahajan and Alex Acero and John C. Platt},
  title={{Hidden conditional random fields for phone classification}},
  booktitle={Proc. Interspeech 2005},