ISCA Archive Eurospeech 1999
ISCA Archive Eurospeech 1999

A recombination strategy for multi-band speech recognition based on mutual information criterion

Shigeki Okawa, Takehiro Nakajima, Katsuhiko Shirai

This paper presents a recombination strategy for multi-band automatic speech recognition (MB-ASR). Several recent works have suggested that MB-ASR gives more accurate recognition, especially in noisy acoustic environments. The main issue in this study concerns the sub-band score recombination in MB-ASR framework. Intuitively, it seems very improbable that all sub-band features have the same amount of information for speech recognition. We therefore investigate to weight the contribution from each band at the recombination process by using a strategy derived from the information theory. The quantity of information is well determined by the mutual information between band features and target phoneme categories to be recognized. The experimental results show that the recognition accuracy improves for noisy speech by using three and six stream systems with the proposed approach.


doi: 10.21437/Eurospeech.1999-155

Cite as: Okawa, S., Nakajima, T., Shirai, K. (1999) A recombination strategy for multi-band speech recognition based on mutual information criterion. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 603-606, doi: 10.21437/Eurospeech.1999-155

@inproceedings{okawa99_eurospeech,
  author={Shigeki Okawa and Takehiro Nakajima and Katsuhiko Shirai},
  title={{A recombination strategy for multi-band speech recognition based on mutual information criterion}},
  year=1999,
  booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
  pages={603--606},
  doi={10.21437/Eurospeech.1999-155}
}