2 papers
eess.AS2022
Unify and Conquer: How Phonetic Feature Representation Affects Polyglot Text-To-Speech (TTS)
Ariadna Sanchez, Alessio Falai, Ziyao Zhang +2
An essential design decision for multilingual Neural Text-To-Speech (NTTS) systems is how to represent input linguistic features within the model. Looking at the wide variety of ap…
eess.AS2022
Mix and Match: An Empirical Study on Training Corpus Composition for Polyglot Text-To-Speech (TTS)
Ziyao Zhang, Alessio Falai, Ariadna Sanchez +2
Training multilingual Neural Text-To-Speech (NTTS) models using only monolingual corpora has emerged as a popular way for building voice cloning based Polyglot NTTS systems. In ord…