Language modeling, especially for spontaneous speech, often suffers from a mismatch of utterance segmentations between training and test conditions. In particular, training often uses linguistically-based segments, whereas testing occurs on acoustically determined segments, resulting in degraded performance. We present an N-best rescoring algorithm that removes the effect of segmentation mismatch. Furthermore, we show that explicit language modeling of hidden linguistic segment boundaries is improved by including turn-boundary events in the model.
Cite as: Stolcke, A. (1997) Modeling linguistic segment and turn boundaries for n-best rescoring of spontaneous speech. Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997), 2779-2782, doi: 10.21437/Eurospeech.1997-701
@inproceedings{stolcke97b_eurospeech, author={Andreas Stolcke}, title={{Modeling linguistic segment and turn boundaries for n-best rescoring of spontaneous speech}}, year=1997, booktitle={Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997)}, pages={2779--2782}, doi={10.21437/Eurospeech.1997-701} }