Bootstrapping non-parallel voice conversion from speaker-adaptive text-to-speech

2019/09/14 by Luong, Hieu-Thi, Yamagishi, Junichi
#Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.1909.06532

Abstract

Voice conversion (VC) and text-to-speech (TTS) are two tasks that share a similar objective, generating speech with a target voice. However, they are usually developed independently under vastly different frameworks. In this paper, we propose a methodology to bootstrap a VC system from a pretrained speaker-adaptive TTS model and unify the techniques as well as the interpretations of these two tasks. Moreover by offloading the heavy data demand to the training stage of the TTS model, our VC system can be built using a small amount of target speaker speech data. It also opens up the possibility of using speech in a foreign unseen language to build the system. Our subjective evaluations show that the proposed framework is able to not only achieve competitive performance in the standard intra-language scenario but also adapt and convert using speech utterances in an unseen language.

Related

• Transfer Learning from Speech Synthesis to Voice Conversion with\n Non-Parallel Training Data
• UnifySpeech: A Unified Framework for Zero-shot Text-to-Speech and Voice Conversion
• Voice Filter: Few-shot text-to-speech speaker adaptation using voice conversion as a post-processing module
• One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization
• Investigation of Using Disentangled and Interpretable Representations for One-shot Cross-lingual Voice Conversion