RAPID ADAPTATION OF N-GRAM LANGUAGE MODELS USING INTER-WORD CORRELATION FOR SPEECH RECOGNITION
作者单位：Department of Information and Communication EngineeringUniversity of Tokyo. Hongo 7-3-1Bunkyu-kuTokyo 113-0033Japan Department of Information and Communication EngineeringUniversity of Tokyo. Hongo 7-3-1Bunkyu-kuTokyo 113-0033Japan
会议名称：《6～(th) International Conference on Spoken Language Processing》
会议日期：2000年
摘 要：正In this paper, we study the fast adaptation problem of n-gram language model under the MAP estimation framework. We have proposed a heuristic method to explore inter-word correlation to accelerate MAP adaptation of n-gram model. According to their correlations, the occurrence of one word can be used to predict all other words in adaptation text. In this way, a large n-gram model can be efficiently adapted with a small amount of adaptation data. The proposed fast adaptation approach is evaluated in a Japanese newspaper corpus. We have observed a signiticant perplexity reduction even when we have only several hundred adaptation sentences.