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 Feldman, Hynek Hermansky, Florian Metze, Richard Rose, Mike Seltzer, Pascal Clark, Ian McGraw, Balakrishnan Varadarajan, Erin Bennett, Benjamin Borschinger, Justin Chiu, Ewan Dunbar, Abdellah Fourtassi, David Harwath & 7 others Chia Ying Lee, Keith Levin, Atta Norouzian, Vijayaditya Peddinti, Rachael Richardson, Thomas Schatz, Samuel Thomas

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

Abstract

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.

LanguageEnglish
Title of host publication2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages8111-8115
Number of pages5
ISBN (Print)9781479903566
DOIs
Publication statusPublished - 18 Oct 2013
Event2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Vancouver, BC, Canada
Duration: 26 May 201331 May 2013

Other

Other2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
CountryCanada
CityVancouver, BC
Period26/05/1331/05/13

Fingerprint

Speech analysis

Cite this

Jansen, A., Dupoux, E., Goldwater, S., Johnson, M., Khudanpur, S., Church, K., ... Thomas, S. (2013). A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition. In 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings (pp. 8111-8115). [6639245] Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICASSP.2013.6639245
Jansen, Aren ; Dupoux, Emmanuel ; Goldwater, Sharon ; Johnson, Mark ; Khudanpur, Sanjeev ; Church, Kenneth ; Feldman, Naomi ; Hermansky, Hynek ; Metze, Florian ; Rose, Richard ; Seltzer, Mike ; Clark, Pascal ; McGraw, Ian ; Varadarajan, Balakrishnan ; Bennett, Erin ; Borschinger, Benjamin ; Chiu, Justin ; Dunbar, Ewan ; Fourtassi, Abdellah ; Harwath, David ; Lee, Chia Ying ; Levin, Keith ; Norouzian, Atta ; Peddinti, Vijayaditya ; Richardson, Rachael ; Schatz, Thomas ; Thomas, Samuel. / A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition. 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings. Piscataway, NJ : Institute of Electrical and Electronics Engineers (IEEE), 2013. pp. 8111-8115
@inproceedings{41983ca239584b9bb1151ebef23e8c58,
title = "A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition",
abstract = "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.",
author = "Aren Jansen and Emmanuel Dupoux and Sharon Goldwater and Mark Johnson and Sanjeev Khudanpur and Kenneth Church and Naomi Feldman and Hynek Hermansky and Florian Metze and Richard Rose and Mike Seltzer and Pascal Clark and Ian McGraw and Balakrishnan Varadarajan and Erin Bennett and Benjamin Borschinger and Justin Chiu and Ewan Dunbar and Abdellah Fourtassi and David Harwath and Lee, {Chia Ying} and Keith Levin and Atta Norouzian and Vijayaditya Peddinti and Rachael Richardson and Thomas Schatz and Samuel Thomas",
year = "2013",
month = "10",
day = "18",
doi = "10.1109/ICASSP.2013.6639245",
language = "English",
isbn = "9781479903566",
pages = "8111--8115",
booktitle = "2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",
address = "United States",

}

Jansen, A, Dupoux, E, Goldwater, S, Johnson, M, Khudanpur, S, Church, K, Feldman, N, Hermansky, H, Metze, F, Rose, R, Seltzer, M, Clark, P, McGraw, I, Varadarajan, B, Bennett, E, Borschinger, B, Chiu, J, Dunbar, E, Fourtassi, A, Harwath, D, Lee, CY, Levin, K, Norouzian, A, Peddinti, V, Richardson, R, Schatz, T & Thomas, S 2013, A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition. in 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings., 6639245, Institute of Electrical and Electronics Engineers (IEEE), Piscataway, NJ, pp. 8111-8115, 2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013, Vancouver, BC, Canada, 26/05/13. https://doi.org/10.1109/ICASSP.2013.6639245

A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition. / Jansen, Aren; Dupoux, Emmanuel; Goldwater, Sharon; Johnson, Mark; Khudanpur, Sanjeev; Church, Kenneth; Feldman, Naomi; Hermansky, Hynek; Metze, Florian; Rose, Richard; Seltzer, Mike; Clark, Pascal; McGraw, Ian; Varadarajan, Balakrishnan; Bennett, Erin; Borschinger, Benjamin; Chiu, Justin; Dunbar, Ewan; Fourtassi, Abdellah; Harwath, David; Lee, Chia Ying; Levin, Keith; Norouzian, Atta; Peddinti, Vijayaditya; Richardson, Rachael; Schatz, Thomas; Thomas, Samuel.

2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings. Piscataway, NJ : Institute of Electrical and Electronics Engineers (IEEE), 2013. p. 8111-8115 6639245.

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

TY - GEN

T1 - A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition

AU - Jansen, Aren

AU - Dupoux, Emmanuel

AU - Goldwater, Sharon

AU - Johnson, Mark

AU - Khudanpur, Sanjeev

AU - Church, Kenneth

AU - Feldman, Naomi

AU - Hermansky, Hynek

AU - Metze, Florian

AU - Rose, Richard

AU - Seltzer, Mike

AU - Clark, Pascal

AU - McGraw, Ian

AU - Varadarajan, Balakrishnan

AU - Bennett, Erin

AU - Borschinger, Benjamin

AU - Chiu, Justin

AU - Dunbar, Ewan

AU - Fourtassi, Abdellah

AU - Harwath, David

AU - Lee, Chia Ying

AU - Levin, Keith

AU - Norouzian, Atta

AU - Peddinti, Vijayaditya

AU - Richardson, Rachael

AU - Schatz, Thomas

AU - Thomas, Samuel

PY - 2013/10/18

Y1 - 2013/10/18

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84890488932&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2013.6639245

DO - 10.1109/ICASSP.2013.6639245

M3 - Conference proceeding contribution

SN - 9781479903566

SP - 8111

EP - 8115

BT - 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway, NJ

ER -

Jansen A, Dupoux E, Goldwater S, Johnson M, Khudanpur S, Church K et al. A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition. In 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE). 2013. p. 8111-8115. 6639245 https://doi.org/10.1109/ICASSP.2013.6639245