Cross-lingual Knowledge Distillation via Flow-based Voice Conversion for Robust Polyglot Text-To-Speech

TL;DR

This paper presents a cross-lingual speech synthesis framework combining voice conversion and TTS, outperforming existing methods and demonstrating robustness across languages, speakers, and data sizes, especially in low-resource scenarios.

Contribution

It introduces a novel multi-stage framework integrating voice conversion with language-independent TTS training, enhancing cross-lingual synthesis performance.

Findings

Outperforms state-of-the-art multilingual TTS models.

Demonstrates robustness across languages, speakers, and data amounts.

Effective in low-resource settings.

Abstract

In this work, we introduce a framework for cross-lingual speech synthesis, which involves an upstream Voice Conversion (VC) model and a downstream Text-To-Speech (TTS) model. The proposed framework consists of 4 stages. In the first two stages, we use a VC model to convert utterances in the target locale to the voice of the target speaker. In the third stage, the converted data is combined with the linguistic features and durations from recordings in the target language, which are then used to train a single-speaker acoustic model. Finally, the last stage entails the training of a locale-independent vocoder. Our evaluations show that the proposed paradigm outperforms state-of-the-art approaches which are based on training a large multilingual TTS model. In addition, our experiments demonstrate the robustness of our approach with different model architectures, languages, speakers and amounts of data. Moreover, our solution is especially beneficial in low-resource settings.