Improved language modeling for conversational applications using sentence quality

Mark Epstein, Bhuvana Ramabhadran, Rajesh Balchandran
2010 2010 IEEE International Conference on Acoustics, Speech and Signal Processing  
In this paper, we propose a new approach to build language models for conversationals system using a a corpus of text as a opposed to a live or a Wizard-of-Oz collection. Each sentence in the corpus is assigned a "quality" that reflects the developer's intuition for how likely that sentence is to be spoken by a real user to the live system. Language Models (LM) are built for each sentence quality and these are subsequently interpolated to produce the final model. We also have built a classifier
more » ... that assigns sentence qualities to the data, and whose subsequent language models achive similar improvements in word and turn error rate.
doi:10.1109/icassp.2010.5494938 dblp:conf/icassp/EpsteinRB10 fatcat:lidqccgikbcq5d6pu5uprayvby