September 22-25, 1997
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.
Bibliographic reference. Stolcke, Andreas (1997): "Modeling linguistic segment and turn boundaries for n-best rescoring of spontaneous speech", In EUROSPEECH-1997, 2779-2782.