Message-driven speech recognition and topic-word extraction
Lists
Only you see this
Abstract
This paper proposes a new formulation for speech recognition/understanding systems. In which the posteriori probability of a speaker's message that the speaker intends to address given an observed acoustic sequence is maximized. This is an extension of the current criterion that maximizes the probability of a word sequence. Among the various possible representations, we employ a co-occurrence score of words measured by mutual information as the conditional probability of a word sequence occurring in a given message. The word sequence hypotheses obtained by bigram and trigram language models are rescored using the co-occurrence score. Experimental results show that the word accuracy is improved by this method. Topic-words which represent the content of a speech signal are then extracted from speech recognition results based on the significance score of each word. When five topic-words are extracted for each broadcast-news article, 82.8% of them are correct in average. This paper also proposes a verbalization-dependent language model which is useful for Japanese dictation systems.
BibTeX
@inproceedings{ohtsuki1999message,
author = {Katsutoshi Ohtsuki and Sadaoki Furui and Atsushi Iwasaki and Naoyuki Sakurai},
title = {{Message-driven speech recognition and topic-word extraction}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {1999},
url = {https://openreview.net/forum?id=pb-5VCIiSV},
}Loading related content...