Discriminative Pronunciation Modeling: A Large-Margin, Feature-Rich Approach

We address the problem of learning the mapping between words and their possible pronunciations in terms of sub-word units. Most previous approaches have involved generative modeling of the distribution of pronunciations, usually trained to maximize likelihood. We propose a discriminative, feature-rich approach using large-margin learning. This approach allows us to optimize an objective closely related to a discriminative task, to incorporate a large number of complex features, and still do inference efficiently. We test the approach on the task of lexical access; that is, the prediction of a word given a phonetic transcription. In experiments on a subset of the Switchboard conversational speech corpus, our models thus far improve classification error rates from a previously published result of 29.1% to about 15%. We find that large-margin approaches outperform conditional random field learning, and that the Passive-Aggressive algorithm for largemargin learning is faster to conver...

• Type: Journal
• Year: 2012
• Where: ACL
• Authors: Hao Tang, Joseph Keshet, Karen Livescu
• Keywords: ACL 2012, Computational Linguistics, Phonetic Transcription, Speech Corpus, Word Units