CiteULike Search Register Log in
CiteULike is a free online bibliography manager. Register and you can start organising your references online.

Getting More Mileage from Web Text Sources for Conversational Speech Language Modeling using Class-dependent Mixtures

by: Ivan Bulyko, Mari Ostendorf
In Proc. HLT-NAACL 2003, Vol. 2 (2003), pp. 7-9.

X Abstract

Sources of training data suitable for language modeling of conversational speech are limited. In this paper, we show how training data can be supplemented with text from the web filtered to match the style and/or topic of the target recognition task, but also that it is possible to get bigger performance gains from the data by using class-dependent interpolation of N-grams. 1

View the full article here:

CiteSeerX Beta

This article has been bookmarked 2 times, initially on 2008-09-05.

2008-09-06 User jmedero
2008-09-05 User zzb3886
Privacy Statement | Terms & Conditions
CiteULike organises scholarly (or academic) papers or literature and provides bibliographic (which means it makes bibliographies) for universities and higher education establishments. It helps undergraduates and postgraduates. People studying for PhDs or in postdoctoral (postdoc) positions. The service is similar in scope to EndNote or RefWorks or any other reference manager like BibTeX, but it is a social bookmarking service for scientists and humanities researchers.