Eta-WavLM: Efficient Speaker Identity Removal in Self-Supervised Speech Representations Using a Simple Linear Equation
This addresses the challenge of removing unwanted speaker variations in speech technologies for applications like voice conversion, though it appears incremental as it builds on existing disentanglement methods.
The paper tackled the problem of disentangling speaker identity from speech representations in self-supervised learning, proposing a linear decomposition method that achieves speaker independence and yields significant improvements in content-driven tasks like voice conversion over state-of-the-art methods.
Self-supervised learning (SSL) has reduced the reliance on expensive labeling in speech technologies by learning meaningful representations from unannotated data. Since most SSL-based downstream tasks prioritize content information in speech, ideal representations should disentangle content from unwanted variations like speaker characteristics in the SSL representations. However, removing speaker information often degrades other speech components, and existing methods either fail to fully disentangle speaker identity or require resource-intensive models. In this paper, we propose a novel disentanglement method that linearly decomposes SSL representations into speaker-specific and speaker-independent components, effectively generating speaker disentangled representations. Comprehensive experiments show that our approach achieves speaker independence and as such, when applied to content-driven tasks such as voice conversion, our representations yield significant improvements over state-of-the-art methods.