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

Taira Tsuchiya, Naohiro Tawara, Testuji Ogawa, Tetsunori Kobayashi

研究成果: Conference contribution

18 被引用数 (Scopus)

抄録

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.

本文言語English
ホスト出版物のタイトル2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ページ2381-2385
ページ数5
ISBN(印刷版)9781538646588
DOI
出版ステータスPublished - 2018 9 10
イベント2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Calgary, Canada
継続期間: 2018 4 152018 4 20

出版物シリーズ

名前ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2018-April
ISSN(印刷版)1520-6149

Other

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

ASJC Scopus subject areas

  • ソフトウェア
  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「Speaker Invariant Feature Extraction for Zero-Resource Languages with Adversarial Learning」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル