Bootstrapping non-parallel voice conversion from speaker-adaptive text-to-speech
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.
arXiv commentAccepted for IEEE ASRU 2019
References in corpus (9)
- Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis
- Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks
- ACVAE-VC: Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder
- Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion
- Combining Adversarial Training and Disentangled Speech Representation for Robust Zero-Resource Subword Modeling
- Fitting New Speakers Based on a Short Untranscribed Sample
- VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019
- A Unified Speaker Adaptation Method for Speech Synthesis using Transcribed and Untranscribed Speech with Backpropagation
- Joint training framework for text-to-speech and voice conversion using multi-source Tacotron and WaveNet