Return to search

The Unsupervised Acquisition of a Lexicon from Continuous Speech

We present an unsupervised learning algorithm that acquires a natural-language lexicon from raw speech. The algorithm is based on the optimal encoding of symbol sequences in an MDL framework, and uses a hierarchical representation of language that overcomes many of the problems that have stymied previous grammar-induction procedures. The forward mapping from symbol sequences to the speech stream is modeled using features based on articulatory gestures. We present results on the acquisition of lexicons and language models from raw speech, text, and phonetic transcripts, and demonstrate that our algorithm compares very favorably to other reported results with respect to segmentation performance and statistical efficiency.

Identiferoai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/7191
Date18 January 1996
CreatorsMarcken, Carl de
Source SetsM.I.T. Theses and Dissertation
Languageen_US
Detected LanguageEnglish
Format27 p., 310643 bytes, 555774 bytes, application/postscript, application/pdf
RelationAIM-1558, CBCL-129

Page generated in 0.0019 seconds