Limited Data Emotional Voice Conversion Leveraging Text-to-Speech: Two-stage Sequence-to-Sequence Training
arXiv:2103.16809
Abstract
Emotional voice conversion (EVC) aims to change the emotional state of an utterance while preserving the linguistic content and speaker identity. In this paper, we propose a novel 2-stage training strategy for sequence-to-sequence emotional voice conversion with a limited amount of emotional speech data. We note that the proposed EVC framework leverages text-to-speech (TTS) as they share a common goal that is to generate high-quality expressive voice. In stage 1, we perform style initialization with a multi-speaker TTS corpus, to disentangle speaking style and linguistic content. In stage 2, we perform emotion training with a limited amount of emotional speech data, to learn how to disentangle emotional style and linguistic information from the speech. The proposed framework can perform both spectrum and prosody conversion and achieves significant improvement over the state-of-the-art baselines in both objective and subjective evaluation.
arXiv commentAccepted by Interspeech 2021
References in corpus (5)
- Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks
- Nonparallel Emotional Speech Conversion
- Improving Sequence-to-Sequence Acoustic Modeling by Adding Text-Supervision
- Expressive TTS Training with Frame and Style Reconstruction Loss
- Emotional Voice Conversion: Theory, Databases and ESD