C
Chia-ying Lee
Researcher at Massachusetts Institute of Technology
Publications - 11
Citations - 683
Chia-ying Lee is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Background noise & Noise. The author has an hindex of 9, co-authored 11 publications receiving 643 citations. Previous affiliations of Chia-ying Lee include National Taiwan University.
Papers
More filters
Proceedings Article
A Nonparametric Bayesian Approach to Acoustic Model Discovery
Chia-ying Lee,James Glass +1 more
TL;DR: An unsupervised model is presented that simultaneously segments the speech, discovers a proper set of sub-word units and learns a Hidden Markov Model for each induced acoustic unit and outperforms a language-mismatched acoustic model.
Journal ArticleDOI
Unsupervised Lexicon Discovery from Acoustic Input
TL;DR: It is shown that the model is competitive with state-of-the-art spoken term discovery systems, and analyses exploring the model’s behavior and the kinds of linguistic structures it learns are presented.
Proceedings ArticleDOI
A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition
Aren Jansen,Emmanuel Dupoux,Sharon Goldwater,Mark Johnson,Sanjeev Khudanpur,Kenneth Church,Naomi H. Feldman,Hynek Hermansky,Florian Metze,Richard Rose,Michael L. Seltzer,Pascal Clark,Ian McGraw,Balakrishnan Varadarajan,Erin Bennett,Benjamin Börschinger,Justin T. Chiu,Ewan Dunbar,Abdellah Fourtassi,David Harwath,Chia-ying Lee,Keith Levin,Atta Norouzian,Vijayaditya Peddinti,Rachael Richardson,Thomas Schatz,Samuel Thomas +26 more
TL;DR: In this article, the authors summarize the accomplishments of a multi-disciplinary workshop exploring the computational and scientific issues surrounding zero resource speech technologies and related models of early language acquisition and present two strategies for integrating zero resource techniques into supervised settings, demonstrating the potential of unsupervised methods to improve mainstream technologies.
Proceedings Article
Collecting Voices from the Cloud
TL;DR: This paper documents efforts to deploy speech-enabled web interfaces to large audiences over the Internet via Amazon Mechanical Turk, an online marketplace for work, using the open source WAMI Toolkit.
Journal Article
One-shot learning of generative speech concepts
TL;DR: This paper investigates how chil- dren and adults readily learn the spoken form of new words from one example – recognizing arbitrary instances of a novel phonological sequence, and excluding non-instances, regard- less of speaker identity and acoustic variability.