INTERSPEECH 2013
14thAnnual Conference of the International Speech Communication Association

Lyon, France
August 25-29, 2013

A Dynamic Programming Framework for Neural Network-Based Automatic Speech Segmentation

Van Zyl van Vuuren (1), Louis ten Bosch (2), Thomas Niesler (1)

(1) University of Stellenbosch, South Africa
(2) Radboud Universiteit Nijmegen, The Netherlands

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.

Full Paper

Bibliographic reference.  Vuuren, Van Zyl van / Bosch, Louis ten / Niesler, Thomas (2013): "A dynamic programming framework for neural network-based automatic speech segmentation", In INTERSPEECH-2013, 2287-2291.