This paper describes an N-gram language model adaptation technique. As an N-gram model requires a large size sample corpus for probability estimation, it is difficult to utilize N-gram model for a specific small task. In this paper, N-gram task adaptation is proposed using large corpus of the general task (TI text) and small corpus of the specific task (AD text). A simple weighting is employed to mix TI and AD text. In addition to mix two texts, the effect of vocabulary is also investigated. The experimental results show that adapted N-gram model with proper vocabulary size has significantly lower perplexity than the task independent models.
|Number of pages
|Published - 1997
|5th European Conference on Speech Communication and Technology, EUROSPEECH 1997 - Rhodes, Greece
Duration: 1997 Sept 22 → 1997 Sept 25
|5th European Conference on Speech Communication and Technology, EUROSPEECH 1997
|97/9/22 → 97/9/25