Sciweavers

Share
EMNLP
2007

Learning Structured Models for Phone Recognition

9 years 3 months ago
Learning Structured Models for Phone Recognition
We present a maximally streamlined approach to learning HMM-based acoustic models for automatic speech recognition. In our approach, an initial monophone HMM is iteratively refined using a split-merge EM procedure which makes no assumptions about subphone structure or context-dependent structure, and which uses only a single Gaussian per HMM state. Despite the much simplified training process, our acoustic model achieves state-of-the-art results on phone classification (where it outperforms almost all other methods) and competitive performance on phone recognition (where it outperforms standard CD triphone / subphone / GMM approaches). We also present an analysis of what is and is not learned by our system.
Slav Petrov, Adam Pauls, Dan Klein
Added 29 Oct 2010
Updated 29 Oct 2010
Type Conference
Year 2007
Where EMNLP
Authors Slav Petrov, Adam Pauls, Dan Klein
Comments (0)
books