Mix and Match: An Empirical Study on Training Corpus Composition for Polyglot Text-To-Speech (TTS)

no code implementations • 4 Jul 2022 • Ziyao Zhang, Alessio Falai, Ariadna Sanchez, Orazio Angelini, Kayoko Yanagisawa

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.

Speech Synthesis Voice Cloning

Unify and Conquer: How Phonetic Feature Representation Affects Polyglot Text-To-Speech (TTS)

no code implementations • 4 Jul 2022 • Ariadna Sanchez, Alessio Falai, Ziyao Zhang, Orazio Angelini, Kayoko Yanagisawa

In this paper, we conduct a comprehensive study comparing multilingual NTTS systems models trained with both representations.

Singing Synthesis: with a little help from my attention

no code implementations • 12 Dec 2019 • Orazio Angelini, Alexis Moinet, Kayoko Yanagisawa, Thomas Drugman

We present UTACO, a singing synthesis model based on an attention-based sequence-to-sequence mechanism and a vocoder based on dilated causal convolutions.