Using a stochastic context-free grammar as a language model for speech recognition
Lists
Only you see this
Abstract
This paper describes a number of experiments in adding new grammatical knowledge to the Berkeley Restaurant Project (BeRP), our medium-vocabulary (1300 word), speaker-independent, spontaneous continuous-speech understanding system. We describe an algorithm for using a probabilistic Earley parser and a stochastic context-free grammar (SCFG) to generate word transition probabilities at each frame for a Viterbi decoder. We show that using an SCFG as a language model improves the word error rate from 34.6% (bigram) to 29.6% (SCFG), and the semantic sentence recognition error from from 39.0% (bigram) to 34.1% (SCFG). In addition, we get a further reduction to 28.8% word error by mixing the bigram and SCFG LMs. We also report on our preliminary results from using discourse-context information in the LM.
BibTeX
@inproceedings{jurafsky1995using,
author = {Daniel Jurafsky and Chuck Wooters and Jonathan Segal and Andreas Stolcke and Eric Fosler and Gary N. Tajchman and Nelson Morgan},
title = {{Using a stochastic context-free grammar as a language model for speech recognition}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {1995},
url = {https://openreview.net/forum?id=eTH1YwFHm0},
}Loading related content...