Domain Adversarial Self-Supervised Speech Representation Learning for Improving Unknown Domain Downstream Tasks

Tomohiro Tanaka; Ryo Masumura; Hiroshi Sato; Mana Ihori; Kohei Matsuura; Takanori Ashihara; Takafumi Moriya

doi:10.21437/interspeech.2022-11414

ScienceGate Book Chapters

JOURNAL ARTICLE

Domain Adversarial Self-Supervised Speech Representation Learning for Improving Unknown Domain Downstream Tasks

Tomohiro Tanaka Ryo Masumura Hiroshi Sato Mana Ihori Kohei Matsuura Takanori Ashihara Takafumi Moriya

Year: 2022 Journal: Interspeech 2022 Pages: 1066-1070

DOI: 10.21437/interspeech.2022-11414

Get Full-Text PDF Get Analytical Report

Keywords:

Computer science Downstream (manufacturing) Adversarial system Domain (mathematical analysis) Representation (politics) Artificial intelligence Natural language processing Speech recognition Engineering Mathematics

Metrics

Cited By

0.24

FWCI (Field Weighted Citation Impact)

Refs

0.42

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Speech Recognition and Synthesis

Physical Sciences → Computer Science → Artificial Intelligence

Domain Adversarial Self-Supervised Speech Representation Learning for Improving Unknown Domain Downstream Tasks

Metrics

Citation History

Topics

Related Documents

Improving Speech Emotion Recognition Using Self-Supervised Learning with Domain-Specific Audiovisual Tasks

Improving Distortion Robustness of Self-supervised Speech Processing Tasks with Domain Adaptation

Dual Acoustic Linguistic Self-supervised Representation Learning for Cross-Domain Speech Recognition

Adversarial Self-Supervised Learning for Out-of-Domain Detection

Self-Supervised Representation Learning From Multi-Domain Data