أعرض تسجيلة المادة بشكل مبسط

dc.creator Marcken, Carl de
dc.date 2004-10-20T20:49:19Z
dc.date 2004-10-20T20:49:19Z
dc.date 1996-01-18
dc.date.accessioned 2013-10-09T02:48:31Z
dc.date.available 2013-10-09T02:48:31Z
dc.date.issued 2013-10-09
dc.identifier AIM-1558
dc.identifier CBCL-129
dc.identifier http://hdl.handle.net/1721.1/7191
dc.identifier.uri http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.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.
dc.format 27 p.
dc.format 310643 bytes
dc.format 555774 bytes
dc.format application/postscript
dc.format application/pdf
dc.language en_US
dc.relation AIM-1558
dc.relation CBCL-129
dc.subject AI
dc.subject MIT
dc.subject Artificial Intelligence
dc.subject induction
dc.subject unsupervised learning
dc.subject language acquisition
dc.subject lexical acquisition
dc.subject continuous speech
dc.title The Unsupervised Acquisition of a Lexicon from Continuous Speech


الملفات في هذه المادة

الملفات الحجم الصيغة عرض

لا توجد أي ملفات مرتبطة بهذه المادة.

هذه المادة تبدو في المجموعات التالية:

أعرض تسجيلة المادة بشكل مبسط