Discrete Unit based Masking for Improving Disentanglement in Voice Conversion
This work addresses a key bottleneck in voice conversion for applications requiring clear speaker identity modification, though it is incremental as it builds on existing encoder-decoder frameworks.
The paper tackles the problem of speaker identity and linguistic content entanglement in voice conversion by introducing a discrete unit-based masking mechanism at the input level, which reduces phonetic dependency and improves performance, achieving a 44% relative improvement in objective intelligibility for attention-based methods.
Voice conversion (VC) aims to modify the speaker's identity while preserving the linguistic content. Commonly, VC methods use an encoder-decoder architecture, where disentangling the speaker's identity from linguistic information is crucial. However, the disentanglement approaches used in these methods are limited as the speaker features depend on the phonetic content of the utterance, compromising disentanglement. This dependency is amplified with attention-based methods. To address this, we introduce a novel masking mechanism in the input before speaker encoding, masking certain discrete speech units that correspond highly with phoneme classes. Our work aims to reduce the phonetic dependency of speaker features by restricting access to some phonetic information. Furthermore, since our approach is at the input level, it is applicable to any encoder-decoder based VC framework. Our approach improves disentanglement and conversion performance across multiple VC methods, showing significant effectiveness, particularly in attention-based method, with 44% relative improvement in objective intelligibility.