Please use this identifier to cite or link to this item:
http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/7191| Title: | The Unsupervised Acquisition of a Lexicon from Continuous Speech |
| Keywords: | AI MIT Artificial Intelligence induction unsupervised learning language acquisition lexical acquisition continuous speech |
| Issue Date: | 9-Oct-2013 |
| Description: | 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. |
| URI: | http://koha.mediu.edu.my:8181/xmlui/handle/1721 |
| Other Identifiers: | AIM-1558 CBCL-129 http://hdl.handle.net/1721.1/7191 |
| Appears in Collections: | MIT Items |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.