An end-to-end TTS model with pronunciation predictor

Recent end-to-end TTS models generate human-like natural speech in real-time, but they produce pronunciation errors which cause the degradation of the naturalness of synthesized speech. In this paper, we investigate a method to alleviate the mispronunciation problem, one of the challenges in end-to-...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	International journal of speech technology 2022, Vol.25 (4), p.1013-1024
Hauptverfasser:	Han, Chol-Jin, Ri, Un-Chol, Mun, Song-Il, Jang, Kang-Song, Han, Song-Yun
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial Intelligence Coders Deep learning Engineering Error analysis Errors Naturalness Phonemes Pronunciation Signal,Image and Speech Processing Social Sciences Speech recognition Speech synthesis Text-to-speech Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!