Uncertainty estimation of DNN classifiers

Sri Harish Mallidi, Tetsuji Ogawa, Hynek Hermansky

Research output: Chapter in Book/Report/Conference proceedingConference contribution

21 Citations (Scopus)

Abstract

New efficient measures for estimating uncertainty of deep neural network (DNN) classifiers are proposed and successfully applied to multistream-based unsupervised adaptation of ASR systems to address uncertainty derived from noise. The proposed measure is the error from associative memory models trained on outputs of a DNN. In the present study, an attempt is made to use autoencoders for remembering the property of data. Another measure proposed is an extension of the M-measure, which computes the divergences of probability estimates spaced at specific time intervals. The extended measure results in an improved reliability by considering the latent information of phoneme duration. Experimental comparisons carried out in a multistream-based ASR paradigm demonstrates that the proposed measures yielded improvements over the multistyle trained system and system selected based on existing measures. Fusion of the proposed measures achieved almost the same performance as the oracle system selection.

Original languageEnglish
Title of host publication2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages283-288
Number of pages6
ISBN (Electronic)9781479972913
DOIs
Publication statusPublished - 2016 Feb 10
EventIEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015 - Scottsdale, United States
Duration: 2015 Dec 132015 Dec 17

Publication series

Name2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015 - Proceedings

Other

OtherIEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015
Country/TerritoryUnited States
CityScottsdale
Period15/12/1315/12/17

Keywords

  • Autoencoder
  • M-delta measure
  • deep neural networks
  • multistream ASR
  • uncertainty estimation

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Uncertainty estimation of DNN classifiers'. Together they form a unique fingerprint.

Cite this