arXiv:2309.03619

Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction

Yusuf Brima, Ulf Krumnack, Simone Pika, Gunther Heidemann

제출 2023-09-07

원문 초록

Self-supervised learning (SSL) has emerged as a promising paradigm for learning flexible speech representations from unlabeled data. By designing pretext tasks that exploit statistical regularities, SSL models can capture useful representations that are transferable to downstream tasks. This study provides an empirical analysis of Barlow Twins (BT), an SSL technique inspired by theories of redundancy reduction in human perception. On downstream tasks, BT representations accelerated learning and transferred across domains. However, limitations exist in disentangling key explanatory factors, with redundancy reduction and invariance alone insufficient for factorization of learned latents into modular, compact, and informative codes. Our ablations study isolated gains from invariance constraints, but the gains were context-dependent. Overall, this work substantiates the potential of Barlow Twins for sample-efficient speech encoding. However, challenges remain in achieving fully hierarchical representations. The analysis methodology and insights pave a path for extensions incorporating further inductive priors and perceptual principles to further enhance the BT self-supervision framework.

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

arXiv:2506.00848공통 태그 Keyword Spotting, Speaker Identification

Speech Unlearning

토론

이 논문과 연결된 포럼 글이 아직 없습니다.