Paper: Towards Incremental End-of-Utterance Detection in Dialogue Systems

ACL ID C08-2003
Title Towards Incremental End-of-Utterance Detection in Dialogue Systems
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2008
Authors

We define the task of incremental or 0- lag utterance segmentation, that is, the task of segmenting an ongoing speech recog- nition stream into utterance units, and present first results. We use a combination of hidden event language model, features from an incremental parser, and acous- tic / prosodic features to train classifiers on real-world conversational data (from the Switchboard corpus). The best classifiers reach an F-score of around 56%, improv- ing over baseline and related work.