VQ-CL: Learning disentangled speech representations with contrastive learning and vector quantization

Voice Conversion(VC) refers to converting the voice characteristics of audio to another one as is said by other people. Recently, more and more studies have focused on disentangle-based VC, which separates the timbre and linguistic content information from a speech signal to effectively achieve VC tasks. However, It's still challenging to extract phoneme-level features from frame-level hidden representations. This paper proposed a novel zero-shot voice conversion framework that utilizes contrastive learning and vector quantization to encourage the frame-level hidden features closer to the phoneme-level linguistic information, called \textbf{VQ-CL}. All objective and subjective experiment results show that VQ-CL has better performance than previous studies in separating content and voice characteristics to improve the sound quality of generated speech.