Towards machines that know when they do not know: Summary of work done at 2014 Frederick Jelinek Memorial Workshop

Hynek Hermansky; Lukáš Burget; Jordan Cohen; Emmanuel Dupoux; Naomi Feldman; John Godfrey; Sanjeev Khudanpur; Matthew Maciejewski; Sri Harish Mallidi; Anjali Menon; Tetsuji Ogawa; Vijayaditya Peddinti; Richard Rose; Richard Stern; Matthew Wiesner; Karel Veselý

doi:10.1109/ICASSP.2015.7178924

Towards machines that know when they do not know: Summary of work done at 2014 Frederick Jelinek Memorial Workshop

Hynek Hermansky, Lukáš Burget, Jordan Cohen, Emmanuel Dupoux, Naomi Feldman, John Godfrey, Sanjeev Khudanpur, Matthew Maciejewski, Sri Harish Mallidi, Anjali Menon, Tetsuji Ogawa, Vijayaditya Peddinti, Richard Rose, Richard Stern, Matthew Wiesner, Karel Veselý

School of Fundamental Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Citations (Scopus)

Abstract

A group of junior and senior researchers gathered as a part of the 2014 Frederick Jelinek Memorial Workshop in Prague to address the problem of predicting the accuracy of a nonlinear Deep Neural Network probability estimator for unknown data in a different application domain from the domain in which the estimator was trained. The paper describes the problem and summarizes approaches that were taken by the group¹.

Original language	English
Title of host publication	2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	5009-5013
Number of pages	5
ISBN (Electronic)	9781467369978
DOIs	https://doi.org/10.1109/ICASSP.2015.7178924
Publication status	Published - 2015 Aug 4
Event	40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Brisbane, Australia Duration: 2014 Apr 19 → 2014 Apr 24

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	2015-August
ISSN (Print)	1520-6149

Other

Other	40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015
Country/Territory	Australia
City	Brisbane
Period	14/4/19 → 14/4/24

Keywords

Performance monitoring
confidence estimation
multistream recognition of speech

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.2015.7178924

Cite this

Hermansky, H., Burget, L., Cohen, J., Dupoux, E., Feldman, N., Godfrey, J., Khudanpur, S., Maciejewski, M., Mallidi, S. H., Menon, A., Ogawa, T., Peddinti, V., Rose, R., Stern, R., Wiesner, M., & Veselý, K. (2015). Towards machines that know when they do not know: Summary of work done at 2014 Frederick Jelinek Memorial Workshop. In 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings (pp. 5009-5013). Article 7178924 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2015-August). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2015.7178924

Towards machines that know when they do not know: Summary of work done at 2014 Frederick Jelinek Memorial Workshop. / Hermansky, Hynek; Burget, Lukáš; Cohen, Jordan et al.
2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. p. 5009-5013 7178924 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2015-August).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Hermansky, H, Burget, L, Cohen, J, Dupoux, E, Feldman, N, Godfrey, J, Khudanpur, S, Maciejewski, M, Mallidi, SH, Menon, A, Ogawa, T, Peddinti, V, Rose, R, Stern, R, Wiesner, M & Veselý, K 2015, Towards machines that know when they do not know: Summary of work done at 2014 Frederick Jelinek Memorial Workshop. in 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings., 7178924, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2015-August, Institute of Electrical and Electronics Engineers Inc., pp. 5009-5013, 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015, Brisbane, Australia, 14/4/19. https://doi.org/10.1109/ICASSP.2015.7178924

Hermansky H, Burget L, Cohen J, Dupoux E, Feldman N, Godfrey J et al. Towards machines that know when they do not know: Summary of work done at 2014 Frederick Jelinek Memorial Workshop. In 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2015. p. 5009-5013. 7178924. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2015.7178924

Hermansky, Hynek ; Burget, Lukáš ; Cohen, Jordan et al. / Towards machines that know when they do not know : Summary of work done at 2014 Frederick Jelinek Memorial Workshop. 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 5009-5013 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{05f6b23a85704070a83d89568290d11e,

title = "Towards machines that know when they do not know: Summary of work done at 2014 Frederick Jelinek Memorial Workshop",

abstract = "A group of junior and senior researchers gathered as a part of the 2014 Frederick Jelinek Memorial Workshop in Prague to address the problem of predicting the accuracy of a nonlinear Deep Neural Network probability estimator for unknown data in a different application domain from the domain in which the estimator was trained. The paper describes the problem and summarizes approaches that were taken by the group1.",

keywords = "Performance monitoring, confidence estimation, multistream recognition of speech",

author = "Hynek Hermansky and Luk{\'a}{\v s} Burget and Jordan Cohen and Emmanuel Dupoux and Naomi Feldman and John Godfrey and Sanjeev Khudanpur and Matthew Maciejewski and Mallidi, {Sri Harish} and Anjali Menon and Tetsuji Ogawa and Vijayaditya Peddinti and Richard Rose and Richard Stern and Matthew Wiesner and Karel Vesel{\'y}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 ; Conference date: 19-04-2014 Through 24-04-2014",

year = "2015",

month = aug,

day = "4",

doi = "10.1109/ICASSP.2015.7178924",

language = "English",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "5009--5013",

booktitle = "2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings",

}

TY - GEN

T1 - Towards machines that know when they do not know

T2 - 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

AU - Hermansky, Hynek

AU - Burget, Lukáš

AU - Cohen, Jordan

AU - Dupoux, Emmanuel

AU - Feldman, Naomi

AU - Godfrey, John

AU - Khudanpur, Sanjeev

AU - Maciejewski, Matthew

AU - Mallidi, Sri Harish

AU - Menon, Anjali

AU - Ogawa, Tetsuji

AU - Peddinti, Vijayaditya

AU - Rose, Richard

AU - Stern, Richard

AU - Wiesner, Matthew

AU - Veselý, Karel

PY - 2015/8/4

Y1 - 2015/8/4

N2 - A group of junior and senior researchers gathered as a part of the 2014 Frederick Jelinek Memorial Workshop in Prague to address the problem of predicting the accuracy of a nonlinear Deep Neural Network probability estimator for unknown data in a different application domain from the domain in which the estimator was trained. The paper describes the problem and summarizes approaches that were taken by the group1.

AB - A group of junior and senior researchers gathered as a part of the 2014 Frederick Jelinek Memorial Workshop in Prague to address the problem of predicting the accuracy of a nonlinear Deep Neural Network probability estimator for unknown data in a different application domain from the domain in which the estimator was trained. The paper describes the problem and summarizes approaches that were taken by the group1.

KW - Performance monitoring

KW - confidence estimation

KW - multistream recognition of speech

UR - http://www.scopus.com/inward/record.url?scp=84946071181&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946071181&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2015.7178924

DO - 10.1109/ICASSP.2015.7178924

M3 - Conference contribution

AN - SCOPUS:84946071181

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 5009

EP - 5013

BT - 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 19 April 2014 through 24 April 2014

ER -

Towards machines that know when they do not know: Summary of work done at 2014 Frederick Jelinek Memorial Workshop

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this