PhoAudiobook is a 941-hour Vietnamese audiobook dataset used to fine-tune and compare three zero-shot TTS models, with reported quality gains over a viVoice-trained baseline.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Zero-Shot Text-to-Speech for Vietnamese
PhoAudiobook is a 941-hour Vietnamese audiobook dataset used to fine-tune and compare three zero-shot TTS models, with reported quality gains over a viVoice-trained baseline.