arXiv:2402.18932

Extending Multilingual Speech Synthesis to 100+ Languages without Transcribed Data

Takaaki Saeki, Gary Wang, Nobuyuki Morioka, Isaac Elias, Kyle Kastner, Fadi Biadsy, Andrew Rosenberg, Bhuvana Ramabhadran, Heiga Zen, Françoise Beaufays, Hadar Shemtov

제출 2024-02-29

원문 초록

Collecting high-quality studio recordings of audio is challenging, which limits the language coverage of text-to-speech (TTS) systems. This paper proposes a framework for scaling a multilingual TTS model to 100+ languages using found data without supervision. The proposed framework combines speech-text encoder pretraining with unsupervised training using untranscribed speech and unspoken text data sources, thereby leveraging massively multilingual joint speech and text representation learning. Without any transcribed speech in a new language, this TTS model can generate intelligible speech in >30 unseen languages (CER difference of <10% to ground truth). With just 15 minutes of transcribed, found data, we can reduce the intelligibility difference to 1% or less from the ground-truth, and achieve naturalness scores that match the ground-truth in several languages.

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

토론

이 논문과 연결된 포럼 글이 아직 없습니다.