期刊
PROCEEDINGS OF THE IEEE
卷 88, 期 8, 页码 1279-1296出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/5.880084
关键词
latent semantic analysis; multispan integration; n-grams; speech recognition; statistical language modeling
Statistical language models used in large-vocabulary speech recognition must properly encapsulate the various constraints, both focal and global, present in the language. While local constraints are readily captured through n-gram modeling, global constraints, such as long-term semantic dependencies, have been more difficult to handle within a data-driven formalism. This paper focuses on the use of latent semantic analysis, a paradigm that automatically uncovers the salient semantic relationships between words and documents in a given corpus. In this approach, (discrete) words and documents are mapped onto a (continuous) semantic vector space, in which familiar clustering techniques ran be applied. This leads to the specification of a powerful framework for automatic semantic classification, as well as the derivation of several language model families with various smoothing properties. Because of their large-span nature, these language models are well suited to complement conventional n-grams. An integrative formulation is proposed for harnessing this synergy, in which the latent semantic information is used to adjust the standard n-gram probability. Such hybrid language modeling compares favorably with the corresponding n-gram baseline: experiments conducted on the Wall Street Journal domain show a reduction in average word error rate of over 20%. This paper concludes with a discussion of intrinsic tradeoffs, such as the influence of training data selection on the resulting performance.
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