Unet-tts: Improving Unseen Speaker And Style Transfer In One-shot Voice Cloning
2021 · Rui Li, Dong Pu, Minnie Huang, et al.
Abstract
One-shot voice cloning aims to transform speaker voice and speaking style in speech synthesized from a text-to-speech (TTS) system, where only a shot recording from the target reference speech can be used. Out-of-domain transfer is still a challenging task, and one important aspect that impacts the accuracy and similarity of synthetic speech is the conditional representations carrying speaker or style cues extracted from the limited references. In this paper, we present a novel one-shot voice cloning algorithm called Unet-TTS that has good generalization ability for unseen speakers and styles. Based on a skip-connected U-net structure, the new model can efficiently discover speaker-level and utterance-level spectral feature details from the reference audio, enabling accurate inference of complex acoustic characteristics as well as imitation of speaking styles into the synthetic speech. According to both subjective and objective evaluations of similarity, the new model outperforms both
Authors
(none)
Tags
Stats
Related papers
- U-style: Cascading U-nets With Multi-level Speaker And Style Modeling For Zero-shot Voice Cloning (2023)6.77
- One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation (2021)8.09
- Meta-voice: Fast Few-shot Style Transfer For Expressive Voice Cloning Using Meta Learning (2021)0.00
- Improving Performance Of Seen And Unseen Speech Style Transfer In End-to-end Neural TTS (2021)6.34
- Investigating On Incorporating Pretrained And Learnable Speaker Representations For Multi-speaker Multi-style Text-to-speech (2021)11.67
- Voice Cloning: A Multi-speaker Text-to-speech Synthesis Approach Based On Transfer Learning (2021)0.00
- Controlspeech: Towards Simultaneous And Independent Zero-shot Speaker Cloning And Zero-shot Language Style Control (2024)9.40
- Improving Zero-shot Voice Style Transfer Via Disentangled Representation Learning (2021)0.00