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.

• Type: Conference
• Year: 2007
• Where: EMNLP
• Authors: Slav Petrov, Adam Pauls, Dan Klein
• Keywords: Acoustic Model, EMNLP 2007, HMM-based Acoustic Models, Initial Monophone Hmm, Natural Language Processing