This paper presents an approach for incorporating prosodic knowledge into the language modelling component of a speech recogniser. We formulate features for a maximum entropy language model which capture various aspects of the relationships between prosody, syntax and the spoken word sequence. Maximum entropy is a powerful modelling technique, and well suited to modelling prosodic information. Tests conducted on the Boston University Radio Speech Corpus using this model showed improvements in perplexity, and n-best rescoring results also demonstrated small but statistically significant gains.
Cite as: Chan, O., Togneri, R. (2006) Prosodic features for a maximum entropy language model. Proc. Interspeech 2006, paper 1150-Wed2CaP.2, doi: 10.21437/Interspeech.2006-512
@inproceedings{chan06b_interspeech,
author={Oscar Chan and Roberto Togneri},
title={{Prosodic features for a maximum entropy language model}},
year=2006,
booktitle={Proc. Interspeech 2006},
pages={paper 1150-Wed2CaP.2},
doi={10.21437/Interspeech.2006-512}
}