ISCA Archive Interspeech 2013
ISCA Archive Interspeech 2013

A dynamic programming framework for neural network-based automatic speech segmentation

Van Zyl van Vuuren, Louis ten Bosch, Thomas Niesler

Neural networks have recently been shown to be a very effective approach to the unconstrained segmentation of speech into phoneme-like units. The neural network is trained to indicate when a short local sequence of feature vectors is associated with a segment boundary, and when it is not. Although this approach delivers state-of-the-art performance, it is prone to oversegmentation at ambiguous segment boundaries. To address this, we propose the incorporation of the neural network segmenter into a dynamic programming (DP) framework. We evaluate the DP-based approach on the TIMIT corpus, and show that it leads to improved performance.


doi: 10.21437/Interspeech.2013-536

Cite as: Vuuren, V.Z.v., Bosch, L.t., Niesler, T. (2013) A dynamic programming framework for neural network-based automatic speech segmentation. Proc. Interspeech 2013, 2287-2291, doi: 10.21437/Interspeech.2013-536

@inproceedings{vuuren13_interspeech,
  author={Van Zyl van Vuuren and Louis ten Bosch and Thomas Niesler},
  title={{A dynamic programming framework for neural network-based automatic speech segmentation}},
  year=2013,
  booktitle={Proc. Interspeech 2013},
  pages={2287--2291},
  doi={10.21437/Interspeech.2013-536}
}