We investigate the problem of acoustic modeling in which prior language-specific knowledge and transcribed data are unavailable. We present an unsupervised model that simultaneously segments the speech, discovers a proper set of sub-word units (e.g., phones) and learns a Hidden Markov Model (HMM) for each induced acoustic unit. Our approach is formulated as a Dirichlet process mixture model in which each mixture is an HMM that represents a sub-word unit. We apply our model to the TIMIT corpus, and the results demonstrate that our model discovers sub-word units that are highly correlated with English phones and also produces better segmentation than the state-of-the-art unsupervised baseline. We test the quality of the learned acoustic models on a spoken term detection task. Compared to the baselines, our model improves the relative precision of top hits by at least 22.1 % and outperforms a language-mismatched acoustic model.
展开▼
