Publication Details

TOWARDS MACHINES THAT KNOW WHEN THEY DO NOT KNOW: SUMMARY OF WORK DONE AT 2014 FREDERICK JELINEK MEMORIAL WORKSHOP

HEŘMANSKÝ Hynek, BURGET Lukáš, COHEN Jordan, DUPOUX Emmanuel, FELDMAN Naomi, GODFREY John, KHUDANPUR Sanjeev, MACIEJEWSKI Matthew, MALLIDI Sri Harish, MENON Anjali, OGAWA Tetsuji, PEDDINTI Vijayaditya, ROSE Richard, STERN Richard, WIESNER Matthew and VESELÝ Karel. Towards Machines That Know When They Do Not Know: Summary of Work Done at 2014 FREDERICK JELINEK MEMORIAL WORKSHOP. In: Proceedings of 2015 IEEE International Conference on Acoustics, Speech and Signal Processing. South Brisbane, Queensland: IEEE Signal Processing Society, 2015, pp. 5009-5013. ISBN 978-1-4673-6997-8. Available from: https://ieeexplore.ieee.org/document/7178924
Czech title
Směrem ke strojům, které vědí, když nevědí - souhrn práce na 2014 Frederick Jelinek Memorial Workshop
Type
conference paper
Language
english
Authors
Heřmanský Hynek, prof. Ing., Dr.Eng. (JHU)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Cohen Jordan (SPMD)
Dupoux Emmanuel (ENS)
Feldman Naomi (UMD)
Godfrey John (UMD)
Khudanpur Sanjeev (JHU)
Maciejewski Matthew (JHU)
Mallidi Sri Harish (AmazonCom)
Menon Anjali (CMU)
Ogawa Tetsuji, Ph.D. (WasUni)
Peddinti Vijayaditya (JHU)
Rose Richard (MCGILL)
Stern Richard (CMU)
Wiesner Matthew (JHU)
Veselý Karel, Ing., Ph.D. (DCGM FIT BUT)
URL
Keywords

Performance monitoring, confidence estimation, multistream recognition of speech

Abstract

In this paper we have proposed and investigated several new techniques for predicting accuracy of estimation of posterior probabilities of speech sounds on previously unseen data, and have shown the feasibility of this task.

Annotation

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

Published
2015
Pages
5009-5013
Proceedings
Proceedings of 2015 IEEE International Conference on Acoustics, Speech and Signal Processing
Conference
2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), Brisbane, AU
ISBN
978-1-4673-6997-8
Publisher
IEEE Signal Processing Society
Place
South Brisbane, Queensland, AU
DOI
10.1109/ICASSP.2015.7178924
UT WoS
000427402905025
EID Scopus
2-s2.0-84946071181
BibTeX 
@INPROCEEDINGS{FITPUB10955,
   author = "Hynek He\v{r}mansk\'{y} 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 Harish Sri Mallidi and Anjali Menon and Tetsuji Ogawa and Vijayaditya Peddinti and Richard Rose and Richard Stern and Matthew Wiesner and Karel Vesel\'{y}",
   title = "TOWARDS MACHINES THAT KNOW WHEN THEY DO NOT KNOW: SUMMARY OF WORK DONE AT 2014 FREDERICK JELINEK MEMORIAL WORKSHOP",
   pages = "5009--5013",
   booktitle = "Proceedings of 2015 IEEE International Conference on Acoustics, Speech and Signal Processing",
   year = 2015,
   location = "South Brisbane, Queensland, AU",
   publisher = "IEEE Signal Processing Society",
   ISBN = "978-1-4673-6997-8",
   doi = "10.1109/ICASSP.2015.7178924",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/10955"
}
Back to top