Add to Quick Collection
Please use this identifier to cite or link to this item: http://hdl.handle.net/1959.14/265207
1123 Visitors
1568 Hits
0 Downloads
- Title
- A Summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition
- Related
- IEEE International Conference on Acoustics, Speech, and Signal Processing (38th : 2013) (26 - 31 May 2013 : Vancouver, Canada)
- Related
- IEEE International Conference on Acoustics, Speech, and Signal Processing : ICASSP 2013 : proceddings : May 26-31, 2013, Vancouver, British Columbia, Canada, p.8111-8115
- DOI
- 10.1109/ICASSP.2013.6639245
- Publisher
- Piscataway, NJ : IEEE
- Date
- 2013
- Author/Creator
- Jansen, Aren
- Author/Creator
- Dupoux, Emmanuel
- Author/Creator
- Seltzer, Mike
- Author/Creator
- Clark, Pascal
- Author/Creator
- McGraw, Ian
- Author/Creator
- Varadarajan, Balakrishnan
- Author/Creator
- Bennett, Erin
- Author/Creator
- Borschinger, Benjamin
- Author/Creator
- Chiu, Justin
- Author/Creator
- Dunbar, Ewan
- Author/Creator
- Fourtassi, Abdellah
- Author/Creator
- Harwath, David
- Author/Creator
- Goldwater, Sharon
- Author/Creator
- Lee, Chia-ying
- Author/Creator
- Levin, Keith
- Author/Creator
- Norouzian, Atta
- Author/Creator
- Peddinti, Vijayaditya
- Author/Creator
- Richardson, Rachael
- Author/Creator
- Schatz, Thomas
- Author/Creator
- Thomas, Samuel
- Author/Creator
- Johnson, Mark
- Author/Creator
- Khudanpur, Sanjeev
- Author/Creator
- Church, Kenneth
- Author/Creator
- Feldman, Naomi
- Author/Creator
- Hermansky, Hynek
- Author/Creator
- Metze, Florian
- Author/Creator
- Rose, Richard
- Description
- We summarize the accomplishments of a multi-disciplinary workshop exploring the computational and scientific issues surrounding zero resource (unsupervised) speech technologies and related models of early language acquisition. Centered around the tasks of phonetic and lexical discovery, we consider unified evaluation metrics, present two new approaches for improving speaker independence in the absence of supervision, and evaluate the application of Bayesian word segmentation algorithms to automatic subword unit tokenizations. Finally, we present two strategies for integrating zero resource techniques into supervised settings, demonstrating the potential of unsupervised methods to improve mainstream technologies.
- Description
- 5 page(s)
- Subject Keyword
- 080100 Artificial Intelligence and Image Processing
- Resource Type
- conference paper
- Organisation
- Macquarie University. Department of Computing
- Identifier
- http://hdl.handle.net/1959.14/265207
- Identifier
- mq:27908
- Identifier
- ISBN:9781479903566
- Identifier
- mq-rm-2012000553
- Identifier
- mq_res-20131105-151829
- Language
- eng
- Reviewed
Macquarie University ResearchOnline
