Unsupervised Lexicon Discovery from Acoustic Input
Author(s)
Lee, Chia-ying; O'Donnell, Timothy John; Glass, James R.
Download520-1757-1-PB.pdf (641.0Kb)
PUBLISHER_CC
Publisher with Creative Commons License
Creative Commons Attribution
Terms of use
Metadata
Show full item recordAbstract
We present a model of unsupervised phonological lexicon discovery -- the problem of simultaneously learning phoneme-like and word-like units from acoustic input. Our model builds on earlier models of unsupervised phone-like unit discovery from acoustic data (Lee and Glass, 2012), and unsupervised symbolic lexicon discovery using the Adaptor Grammar framework (Johnson et al., 2006), integrating these earlier approaches using a probabilistic model of phonological variation. We show that the model is competitive with state-of-the-art spoken term discovery systems, and present analyses exploring the model's behavior and the kinds of linguistic structures it learns.
Date issued
2015-07Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory; Massachusetts Institute of Technology. Department of Brain and Cognitive SciencesJournal
Transactions of the Association for Computational Linguistics
Publisher
Association for Computational Linguistics
Citation
Lee, Chia-ying, Timothy J. O'Donnell, and James Glass. "Unsupervised Lexicon Discovery from Acoustic Input." Transactions of the Association for Computational Linguistics, Volume 3 (2015). © 2015 Association for Computational Linguistics
Version: Final published version
ISSN
2307-387X