期刊
IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING
卷 8, 期 1, 页码 63-75出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/89.817454
关键词
language modeling; spontaneous speech; variable n-grams
Recent progress in variable n-gram language modeling provides an efficient representation of n-gram models and makes training of higher order n-grams possible. In this paper, me apply the variable n-gram design algorithm to conversational speech, extending the algorithm to learn skips and context-dependent classes to handle conversational speech characteristics such as filler words, repetitions, and other disfluencies. Experiments show that using the extended variable n-gram results in a language model that captures 4-gram context with less than half the parameters of a standard trigram while also improving the test perplexity and recognition accuracy.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据