How Far Are We from Robust Voice Conversion: A Survey
Journal
2021 IEEE Spoken Language Technology Workshop, SLT 2021 - Proceedings
Pages
514-521
Date Issued
2021
Author(s)
Abstract
Voice conversion technologies have been greatly improved in recent years with the help of deep learning, but their capabilities of producing natural sounding utterances in different conditions remain unclear. In this paper, we gave a thorough study of the robustness of known VC models. We also modified these models, such as the replacement of speaker embeddings, to further improve their performances. We found that the sampling rate and audio duration greatly influence voice conversion. All the VC models suffer from unseen data, but AdaIN-VC is relatively more robust. Also, the speaker embedding jointly trained is more suitable for voice conversion than those trained on speaker identification. ? 2021 IEEE.
Subjects
Embeddings; Sampling rates; Speaker identification; Voice conversion; Deep learning
SDGs
Type
conference paper