VQVC+: One-shot voice conversion by vector quantization and U-Net architecture
Journal
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Journal Volume
2020-October
Pages
4691-4695
Date Issued
2020
Author(s)
Abstract
Voice conversion (VC) is a task that transforms the source speaker's timbre, accent, and tones in audio into another one's while preserving the linguistic content. It is still a challenging work, especially in a one-shot setting. Auto-encoder-based VC methods disentangle the speaker and the content in input speech without explicit information about the speaker's identity, so these methods can further generalize to unseen speakers. The disentangle capability is achieved by vector quantization (VQ), adversarial training, or instance normalization (IN). However, the imperfect disentanglement may harm the quality of output speech. In this work, to further improve audio quality, we use the U-Net architecture within an auto-encoder-based VC system. We find that to leverage the U-Net architecture, a strong information bottleneck is necessary. The VQ-based method, which quantizes the latent vectors, can serve the purpose. The objective and the subjective evaluations show that the proposed method performs well in both audio naturalness and speaker similarity. Copyright ? 2020 ISCA
Subjects
Architecture; Learning systems; Signal encoding; Speech communication; Audio quality; Auto encoders; Explicit information; Information bottleneck; Latent vectors; NET architecture; Subjective evaluations; Voice conversion; Vector quantization
SDGs
Type
conference paper