Speaker adversarial training of DPGMM-based feature extractor for zero-resource languages

Yosuke Higuchi, Naohiro Tawara, Tetsunori Kobayashi, Tetsuji Ogawa

研究成果: Conference article査読

3 被引用数 (Scopus)

抄録

We propose a novel framework for extracting speaker-invariant features for zero-resource languages. A deep neural network (DNN)-based acoustic model is normalized against speakers via adversarial training: a multi-task learning process trains a shared bottleneck feature to be discriminative to phonemes and independent of speakers. However, owing to the absence of phoneme labels, zero-resource languages cannot employ adversarial multi-task (AMT) learning for speaker normalization. In this work, we obtain a posteriorgram from a Dirichlet process Gaussian mixture model (DPGMM) and utilize the posterior vector for supervision of the phoneme estimation in the AMT training. The AMT network is designed so that the DPGMM posteriorgram itself is embedded in a speaker-invariant feature space. The proposed network is expected to resolve the potential problem that the posteriorgram may lack reliability as a phoneme representation if the DPGMM components are intermingled with phoneme and speaker information. Based on the Zero Resource Speech Challenges, we conduct phoneme discriminant experiments on the extracted features. The results of the experiments show that the proposed framework extracts discriminative features, suppressing the variety in speakers.

本文言語English
ページ(範囲)266-270
ページ数5
ジャーナルProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
2019-September
DOI
出版ステータスPublished - 2019
イベント20th Annual Conference of the International Speech Communication Association: Crossroads of Speech and Language, INTERSPEECH 2019 - Graz, Austria
継続期間: 2019 9 152019 9 19

ASJC Scopus subject areas

  • 言語および言語学
  • 人間とコンピュータの相互作用
  • 信号処理
  • ソフトウェア
  • モデリングとシミュレーション

フィンガープリント

「Speaker adversarial training of DPGMM-based feature extractor for zero-resource languages」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