Abstract
A new efficient measure for predicting estimation accuracy is proposed and successfully applied to multistream-based unsupervised adaptation of ASR systems to address data uncertainty when the ground-truth is unknown. The proposed measure is an extension of the M-measure, which predicts confidence in the output of a probability estimator by measuring the divergences of probability estimates spaced at specific time intervals. In this study, the M-measure was extended by considering the latent phoneme information, resulting in an improved reliability. Experimental comparisons carried out in a multistream-based ASR paradigm demonstrated that the extended M-measure yields a significant improvement over the original M-measure, especially under narrow-band noise conditions.
Original language | English |
---|---|
Title of host publication | 2016 23rd International Conference on Pattern Recognition, ICPR 2016 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 2222-2227 |
Number of pages | 6 |
ISBN (Electronic) | 9781509048472 |
DOIs | |
Publication status | Published - 2017 Apr 13 |
Event | 23rd International Conference on Pattern Recognition, ICPR 2016 - Cancun, Mexico Duration: 2016 Dec 4 → 2016 Dec 8 |
Other
Other | 23rd International Conference on Pattern Recognition, ICPR 2016 |
---|---|
Country | Mexico |
City | Cancun |
Period | 16/12/4 → 16/12/8 |
Fingerprint
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
Cite this
A new efficient measure for accuracy prediction and its application to multistream-based unsupervised adaptation. / Ogawa, Tetsuji; Mallidi, Sri Harish; Dupoux, Emmanuel; Cohen, Jordan; Feldman, Naomi H.; Hermansky, Hynek.
2016 23rd International Conference on Pattern Recognition, ICPR 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 2222-2227 7899966.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - A new efficient measure for accuracy prediction and its application to multistream-based unsupervised adaptation
AU - Ogawa, Tetsuji
AU - Mallidi, Sri Harish
AU - Dupoux, Emmanuel
AU - Cohen, Jordan
AU - Feldman, Naomi H.
AU - Hermansky, Hynek
PY - 2017/4/13
Y1 - 2017/4/13
N2 - A new efficient measure for predicting estimation accuracy is proposed and successfully applied to multistream-based unsupervised adaptation of ASR systems to address data uncertainty when the ground-truth is unknown. The proposed measure is an extension of the M-measure, which predicts confidence in the output of a probability estimator by measuring the divergences of probability estimates spaced at specific time intervals. In this study, the M-measure was extended by considering the latent phoneme information, resulting in an improved reliability. Experimental comparisons carried out in a multistream-based ASR paradigm demonstrated that the extended M-measure yields a significant improvement over the original M-measure, especially under narrow-band noise conditions.
AB - A new efficient measure for predicting estimation accuracy is proposed and successfully applied to multistream-based unsupervised adaptation of ASR systems to address data uncertainty when the ground-truth is unknown. The proposed measure is an extension of the M-measure, which predicts confidence in the output of a probability estimator by measuring the divergences of probability estimates spaced at specific time intervals. In this study, the M-measure was extended by considering the latent phoneme information, resulting in an improved reliability. Experimental comparisons carried out in a multistream-based ASR paradigm demonstrated that the extended M-measure yields a significant improvement over the original M-measure, especially under narrow-band noise conditions.
UR - http://www.scopus.com/inward/record.url?scp=85019079432&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85019079432&partnerID=8YFLogxK
U2 - 10.1109/ICPR.2016.7899966
DO - 10.1109/ICPR.2016.7899966
M3 - Conference contribution
AN - SCOPUS:85019079432
SP - 2222
EP - 2227
BT - 2016 23rd International Conference on Pattern Recognition, ICPR 2016
PB - Institute of Electrical and Electronics Engineers Inc.
ER -