Generalized linear interpolation of language models

Despite the prevalent use of model combination techniques to improve speech recognition performance on domains with limited data, little prior research has focused on the choice of the actual interpolation model. For merging language models, the most popular approach has been the simple linear inter...

Full description

Saved in:
Bibliographic Details
Published in2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU) pp. 136 - 140
Main Author Bo-June Hsu
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2007
Subjects
adaptation
Adaptation model
Artificial intelligence
Computer science
History
Interpolation
Laboratories
Language modeling
Merging
mixture models
Natural languages
Phase change materials
Speech recognition
Online AccessGet full text

Cover

More Information
Summary:Despite the prevalent use of model combination techniques to improve speech recognition performance on domains with limited data, little prior research has focused on the choice of the actual interpolation model. For merging language models, the most popular approach has been the simple linear interpolation. In this work, we propose a generalization of linear interpolation that computes context-dependent mixture weights from arbitrary features. Results on a lecture transcription task yield up to a 1.0% absolute improvement in recognition word error rate (WER).
ISBN:9781424417452
1424417457
DOI:10.1109/ASRU.2007.4430098