2022/03/30 by Jiachen Lian, Chunlei Zhang, Lian, Jiachen +3 · 5 citations
Computer Science · #Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Music and Audio Processing #Signal Processing (eess.SP) #Speech Recognition and Synthesis #Speech and Audio Processing #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2203.16705
openalex publication_date 2022/03/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Traditional studies on voice conversion (VC) have made progress with parallel training data and known speakers. Good voice conversion quality is obtained by exploring better alignment modules or expressive mapping functions. In this study, we investigate zero-shot VC from a novel perspective of self-supervised disentangled speech representation learning. Specifically, we achieve the disentanglement by balancing the information flow between global speaker representation and time-varying content representation in a sequential variational autoencoder (VAE). A zero-shot voice conversion is performed by feeding an arbitrary speaker embedding and content embeddings to the VAE decoder. Besides that, an on-the-fly data augmentation training strategy is applied to make the learned representation noise invariant. On TIMIT and VCTK datasets, we achieve state-of-the-art performance on both objective evaluation, i.e., speaker verification (SV) on speaker embedding and content embedding, and subjective evaluation, i.e., voice naturalness and similarity, and remains to be robust even with noisy source/target utterances.