Exploring the role of language families for building indic speech synthesisers

A Prakash, HA Murthy - IEEE/ACM Transactions on Audio …, 2022 - ieeexplore.ieee.org
Building end-to-end speech synthesisers for Indian languages is challenging, given the lack
of adequate clean training data and multiple grapheme representations across languages …

Mix and match: an empirical study on training corpus composition for polyglot text-to-speech (TTS)

Z Zhang, A Falai, A Sanchez, O Angelini… - arxiv preprint arxiv …, 2022 - arxiv.org
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 …

Conditioning Text-to-Speech synthesis on dialect accent: a case study

A Falai - amslaurea.unibo.it
Modern text-to-speech systems are modular in many different ways. In recent years, end-
users gained the ability to control speech attributes such as degree of emotion, rhythm and …