ISCA Archive Eurospeech 1999
ISCA Archive Eurospeech 1999

Reviving discrete HMMs: the myth about the superiority of continuous HMMs

Vassilis Digalakis, Stavros Tsakalidis, Leonardo Neumeyer

Despite what is generally believed, we have recently shown that discrete-distribution HMMs can outperform continuous-density HMMs at significantly faster decoding speeds. Recognition performance and decoding speed of the discrete HMMs are improved by using product-code Vector Quantization (VQ) and mixtures of discrete distributions. In this paper, we present efficient training and decoding algorithms for the discrete-mixture HMMs (DMHMMs). Our experimental results show that the high-level of recognition accuracy of continuous mixture-density HMMs (CDHMMs) can be maintained at significantly faster decoding speeds.


doi: 10.21437/Eurospeech.1999-475

Cite as: Digalakis, V., Tsakalidis, S., Neumeyer, L. (1999) Reviving discrete HMMs: the myth about the superiority of continuous HMMs. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 2463-2466, doi: 10.21437/Eurospeech.1999-475

@inproceedings{digalakis99_eurospeech,
  author={Vassilis Digalakis and Stavros Tsakalidis and Leonardo Neumeyer},
  title={{Reviving discrete HMMs: the myth about the superiority of continuous HMMs}},
  year=1999,
  booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
  pages={2463--2466},
  doi={10.21437/Eurospeech.1999-475}
}