Computer Science – Computation and Language
Scientific paper
1995-12-13
Computer Science
Computation and Language
27 page technical report
Scientific paper
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.
No associations
LandOfFree
The Unsupervised Acquisition of a Lexicon from Continuous Speech does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with The Unsupervised Acquisition of a Lexicon from Continuous Speech, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and The Unsupervised Acquisition of a Lexicon from Continuous Speech will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-615696