Kallirroi Georgila: “Using Integer Linear Programming for Detecting Speech Disfluencies”

May 31, 2009 | Boulder, CO

Speaker: Kallirroi Georgila
Host: North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT) Conference

We present a novel two-stage technique for detecting speech disfluencies based on Integer Linear Programming (ILP). In the first stage we use state-of-the-art models for speech disfluency detection, in particular, hidden-event language models, maximum entropy models and conditional random fields. During testing each model proposes possible disfluency labels which are then assessed in the presence of global constraints using ILP. Our experimental results show that by using ILP we can improve significantly the performance of our models with negligible cost in processing time. The less training data is available the larger the improvement due to ILP.