ISCA Archive Eurospeech 1997
ISCA Archive Eurospeech 1997

Segment boundary estimation using recurrent neural networks

Toshiaki Fukada, Sophie Aveline, Mike Schuster, Yoshinori Sagisaka

This paper describes a segment (e.g. phoneme) boundary estimation method based on recurrent neural networks (RNNs). The proposed method only requires acoustic observations to accurately estimate segment boundaries. Experimental results show that the proposed method can estimate segment boundaries significantly better than an HMM based method. Furthermore, we incorporate the RNN based segment boundary estimator into the HMM based and segment based recognition systems. As a result, the segment boundary estimates give useful information for reducing computational complexity and improving recognition performance.


doi: 10.21437/Eurospeech.1997-716

Cite as: Fukada, T., Aveline, S., Schuster, M., Sagisaka, Y. (1997) Segment boundary estimation using recurrent neural networks. Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997), 2839-2842, doi: 10.21437/Eurospeech.1997-716

@inproceedings{fukada97b_eurospeech,
  author={Toshiaki Fukada and Sophie Aveline and Mike Schuster and Yoshinori Sagisaka},
  title={{Segment boundary estimation using recurrent neural networks}},
  year=1997,
  booktitle={Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997)},
  pages={2839--2842},
  doi={10.21437/Eurospeech.1997-716},
  issn={1018-4074}
}