4 |
The Unsupervised Acquisition of a Lexicon from Continuous Speech.
|
|
|
|
In: DTIC AND NTIS (1995)
|
|
BASE
|
|
Show details
|
|
5 |
The Unsupervised Acquisition of a Lexicon from Continuous Speech ...
|
|
|
|
Abstract:
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. ... : 27 page technical report ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/cmp-lg/9512002 https://dx.doi.org/10.48550/arxiv.cmp-lg/9512002
|
|
BASE
|
|
Hide details
|
|
7 |
The Acquisition of a Lexicon from Paired Phoneme Sequences and Semantic Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Methods for Parallelizing Search Paths in Phrasing
|
|
|
|
In: DTIC AND NTIS (1993)
|
|
BASE
|
|
Show details
|
|
|
|