Show simple item record

dc.contributor.authorHuang, Songfangen
dc.contributor.authorRenals, Steveen
dc.date.accessioned2008-02-19T13:37:55Z
dc.date.available2008-02-19T13:37:55Z
dc.date.issued2007
dc.identifier.citationSongfang Huang and Steve Renals. Modeling prosodic features in language models for meetings. In A. Popescu-Belis, S. Renals, and H. Bourlard, editors, Machine Learning for Multimodal Interaction IV, volume 4892 of Lecture Notes in Computer Science, pages 191-202. Springer, 2007.
dc.identifier.urihttp://hdl.handle.net/1842/2136
dc.description.abstractIn this paper we investigate the application of a novel technique for language modeling - a hierarchical Bayesian language model (LM) based on the Pitman-Yor process - on automatic speech recognition (ASR) for multiparty meetings. The hierarchical Pitman-Yor language model (HPYLM), which was originally proposed in the machine learning field, provides a Bayesian interpretation to language modeling. An approximation to the HPYLM recovers the exact formulation of the interpolated Kneser-Ney smoothing method in n-gram models. This paper focuses on the application and scalability of HPYLM on a practical large vocabulary ASR system. Experimental results on NIST RT06s evaluation meeting data verify that HPYLM is a competitive and promising language modeling technique, which consistently performs better than interpolated Kneser-Ney and modified Kneser-Ney n-gram LMs in terms of both perplexity (PPL) and word error rate (WER).en
dc.format.extent251672 bytesen
dc.format.mimetypeapplication/pdfen
dc.language.isoen
dc.publisherSpringer-Verlag Berlin Heidelbergen
dc.subjectspeech technologyen
dc.subjectBayesian language modelen
dc.titleModeling prosodic features in language models for meetings.en
dc.typeConference Paperen


Files in this item

This item appears in the following Collection(s)

Show simple item record