English

Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering

Computation and Language 2023-05-19 v1 Audio and Speech Processing

Abstract

Self-supervised speech representation models have succeeded in various tasks, but improving them for content-related problems using unlabeled data is challenging. We propose speaker-invariant clustering (Spin), a novel self-supervised learning method that clusters speech representations and performs swapped prediction between the original and speaker-perturbed utterances. Spin disentangles speaker information and preserves content representations with just 45 minutes of fine-tuning on a single GPU. Spin improves pre-trained networks and outperforms prior methods in speech recognition and acoustic unit discovery.

Keywords

Cite

@article{arxiv.2305.11072,
  title  = {Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering},
  author = {Heng-Jui Chang and Alexander H. Liu and James Glass},
  journal= {arXiv preprint arXiv:2305.11072},
  year   = {2023}
}

Comments

Accepted to Interspeech 2023

R2 v1 2026-06-28T10:38:22.588Z