Analysis of Voice Conversion and Code-Switching Synthesis Using VQ-VAE
Shuvayanti Das, Jennifer Williams, Catherine Lai

TL;DR
This paper analyzes the quality of multilingual speech synthesis using VQ-VAE, focusing on voice conversion and code-switching across four languages, revealing challenges like quality degradation with more switches and accent transfer effects.
Contribution
It provides a detailed analysis of multilingual VQ-VAE speech synthesis, highlighting limitations and potential directions for improvement in handling code-switching and voice conversion.
Findings
Speech quality decreases with more language switches
Accent transfer occurs during cross-language voice conversion
Assessment of accent transfer remains challenging
Abstract
This paper presents an analysis of speech synthesis quality achieved by simultaneously performing voice conversion and language code-switching using multilingual VQ-VAE speech synthesis in German, French, English and Italian. In this paper, we utilize VQ code indices representing phone information from VQ-VAE to perform code-switching and a VQ speaker code to perform voice conversion in a single system with a neural vocoder. Our analysis examines several aspects of code-switching including the number of language switches and the number of words involved in each switch. We found that speech synthesis quality degrades after increasing the number of language switches within an utterance and decreasing the number of words. We also found some evidence of accent transfer when performing voice conversion across languages as observed when a speaker's original language differs from the language…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSpeech Recognition and Synthesis · Speech and dialogue systems · Phonetics and Phonology Research
MethodsVQ-VAE
