ISCA Archive SpeechProsody 2008
ISCA Archive SpeechProsody 2008

Exploiting prosodic breaks in language modeling with random forests

Yi Su, Frederick Jelinek

We propose a novel method of exploiting prosodic breaks in language modeling for automatic speech recognition (ASR) based on the random forest language model (RFLM), which is a collection of randomized decision tree language models and can potentially ask any questions about the history in order to predict the future. We demonstrate how questions about prosodic breaks can be easily incorporated into the RFLM and present two language models which treat prosodic breaks as observable and hidden variables, respectively. Meanwhile, we show empirically that a finer grained prosodic break is needed for language modeling. Experimental results showed that given prosodic breaks, we were able to reduce the LM perplexity by a significant margin, suggesting a prosodic N-best rescoring approach for ASR.


Cite as: Su, Y., Jelinek, F. (2008) Exploiting prosodic breaks in language modeling with random forests. Proc. Speech Prosody 2008, 91-94

@inproceedings{su08_speechprosody,
  author={Yi Su and Frederick Jelinek},
  title={{Exploiting prosodic breaks in language modeling with random forests}},
  year=2008,
  booktitle={Proc. Speech Prosody 2008},
  pages={91--94}
}