Extending Multilingual Speech Synthesis to 100+ Languages without Transcribed Data
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.
RapFlow-TTS: Rapid and High-Fidelity Text-to-Speech with Improved Consistency Flow Matching
InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems
ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching
NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech
Speech Quality Assessment Model Based on Mixture of Experts: System-Level Performance Enhancement and Utterance-Level Challenge Analysis
UmbraTTS: Adapting Text-to-Speech to Environmental Contexts with Flow Matching
토론
이 논문과 연결된 포럼 글이 아직 없습니다.