Zero-Shot Text-to-Speech for Vietnamese
Thi Vu, Linh The Nguyen, Dat Quoc Nguyen
Abstract
This paper introduces PhoAudiobook, a newly curated dataset comprising 941 hours of high-quality audio for Vietnamese text-to-speech. Using PhoAudiobook, we conduct experiments on three leading zero-shot TTS models: VALL-E, VoiceCraft, and XTTS-V2. Our findings demonstrate that PhoAudiobook consistently enhances model performance across various metrics. Moreover, VALL-E and VoiceCraft exhibit superior performance in synthesizing short sentences, highlighting their robustness in handling diverse linguistic contexts. We publicly release PhoAudiobook to facilitate further research and development in Vietnamese text-to-speech.
Related Papers
Hear Your Code Fail, Voice-Assisted Debugging for Python2025-07-20NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech2025-07-17P.808 Multilingual Speech Enhancement Testing: Approach and Results of URGENT 2025 Challenge2025-07-15An Empirical Evaluation of AI-Powered Non-Player Characters' Perceived Realism and Performance in Virtual Reality Environments2025-07-14ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching2025-07-12Exploiting Leaderboards for Large-Scale Distribution of Malicious Models2025-07-11MIDI-VALLE: Improving Expressive Piano Performance Synthesis Through Neural Codec Language Modelling2025-07-11Speech Quality Assessment Model Based on Mixture of Experts: System-Level Performance Enhancement and Utterance-Level Challenge Analysis2025-07-08