Trigger-Based Language Model Adaptation for Automatic Transcription of Panel Discussions


IEICE TRANSACTIONS on Information and Systems   Vol.E89-D   No.3   pp.1024-1031
Publication Date: 2006/03/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e89-d.3.1024
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Section on Statistical Modeling for Speech Processing)
Category: Speech Recognition
speech recognition,  language model,  trigger-based language model,  TF/IDF,  

Full Text: PDF>>
Buy this Article

We present a novel trigger-based language model adaptation method oriented to the transcription of meetings. In meetings, the topic is focused and consistent throughout the whole session, therefore keywords can be correlated over long distances. The trigger-based language model is designed to capture such long-distance dependencies, but it is typically constructed from a large corpus, which is usually too general to derive task-dependent trigger pairs. In the proposed method, we make use of the initial speech recognition results to extract task-dependent trigger pairs and to estimate their statistics. Moreover, we introduce a back-off scheme that also exploits the statistics estimated from a large corpus. The proposed model reduced the test-set perplexity considerably more than the typical trigger-based language model constructed from a large corpus, and achieved a remarkable perplexity reduction of 44% over the baseline when combined with an adapted trigram language model. In addition, a reduction in word error rate was obtained when using the proposed language model to rescore word graphs.