The Unsupervised Acquisition of a Lexicon from Continuous Speech

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 stym...

Full description

Bibliographic Details
Main Author: Marcken, Carl de
Language:en_US
Published: 2004
Subjects:
AI
MIT
Artificial Intelligence
induction
unsupervised learning
language acquisition
lexical acquisition
continuous speech
Online Access:http://hdl.handle.net/1721.1/7191

Internet

http://hdl.handle.net/1721.1/7191

Similar Items