USAT: A Universal Speaker-Adaptive Text-to-Speech Approach

arXiv:2404.18094v1 Announce Type: cross
Abstract: Conventional text-to-speech (TTS) research has predominantly focused on enhancing the quality of synthesized speech for speakers in the training dataset. The challenge of synthesizing lifelike speech for unseen, out-of-dataset speakers, especially those with limited reference data, remains a significant and unresolved problem. While zero-shot or few-shot speaker-adaptive TTS approaches have been explored, they have many limitations. Zero-shot approaches tend to suffer from insufficient generalization performance to reproduce the voice of speakers with heavy accents. While …

abstract arxiv challenge cs.ai cs.cl cs.sd data dataset few-shot quality reference research speaker speakers speech synthesized text text-to-speech training tts type universal while zero-shot