Speaker Invariant Feature Extraction for Zero-Resource Languages with Adversarial Learning

Taira Tsuchiya, Naohiro Tawara, Testuji Ogawa, Tetsunori Kobayashi

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

15 Citations (Scopus)

Abstract

We introduce a novel type of representation learning to obtain a speaker invariant feature for zero-resource languages. Speaker adaptation is an important technique to build a robust acoustic model. For a zero-resource language, however, conventional model-dependent speaker adaptation methods such as constrained maximum likelihood linear regression are insufficient because the acoustic model of the target language is not accessible. Therefore, we introduce a model-independent feature extraction based on a neural network. Specifically, we introduce a multi-task learning to a bottleneck feature-based approach to make bottleneck feature invariant to a change of speakers. The proposed network simultaneously tackles two tasks: phoneme and speaker classifications. This network trains a feature extractor in an adversarial manner to allow it to map input data into a discriminative representation to predict phonemes, whereas it is difficult to predict speakers. We conduct phone discriminant experiments in Zero Resource Speech Challenge 2017. Experimental results showed that our multi-task network yielded more discriminative features eliminating the variety in speakers.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2381-2385
Number of pages5
ISBN (Print)9781538646588
DOIs
Publication statusPublished - 2018 Sep 10
Event2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Calgary, Canada
Duration: 2018 Apr 152018 Apr 20

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2018-April
ISSN (Print)1520-6149

Other

Other2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018
CountryCanada
CityCalgary
Period18/4/1518/4/20

Keywords

  • Adversarial multi-task learning
  • FMLLR
  • Representation learning
  • Speaker invariant feature
  • Zero resource speech challenge

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Speaker Invariant Feature Extraction for Zero-Resource Languages with Adversarial Learning'. Together they form a unique fingerprint.

Cite this