Using Joint Training Speaker Encoder With Consistency Loss To Achieve Cross-lingual Voice Conversion And Expressive Voice Conversion
2023 · Houjian Guo, Chaoran Liu, Carlos Toshinori Ishi, et al.
Abstract
Voice conversion systems have made significant advancements in terms of naturalness and similarity in common voice conversion tasks. However, their performance in more complex tasks such as cross-lingual voice conversion and expressive voice conversion remains imperfect. In this study, we propose a novel approach that combines a jointly trained speaker encoder and content features extracted from the cross-lingual speech recognition model Whisper to achieve high-quality cross-lingual voice conversion. Additionally, we introduce a speaker consistency loss to the joint encoder, which improves the similarity between the converted speech and the reference speech. To further explore the capabilities of the joint speaker encoder, we use the phonetic posteriorgram as the content feature, which enables the model to effectively reproduce both the speaker characteristics and the emotional aspects of the reference speech.
Authors
(none)
Tags
Stats
Related papers
- Building Bilingual And Code-switched Voice Conversion With Limited Training Data Using Embedding Consistency Loss (2021)0.00
- Learning In Your Voice: Non-parallel Voice Conversion Based On Speaker Consistency Loss (2020)0.00
- Accent And Speaker Disentanglement In Many-to-many Voice Conversion (2020)10.35
- Cross-lingual Text-to-speech Using Multi-task Learning And Speaker Classifier Joint Training (2022)0.00
- Audiovisual Speaker Conversion: Jointly And Simultaneously Transforming Facial Expression And Acoustic Characteristics (2018)4.52
- Building Multi Lingual TTS Using Cross Lingual Voice Conversion (2020)0.00
- Towards Natural And Controllable Cross-lingual Voice Conversion Based On Neural TTS Model And Phonetic Posteriorgram (2021)0.00
- Autocycle-vc: Towards Bottleneck-independent Zero-shot Cross-lingual Voice Conversion (2023)0.00