Marius Cotescu — accepted AI-conference papers

2023

Modelling Low-Resource Accents Without Accent-Specific TTS Frontend

Georgi Tinchev, Marta Czarnowska, Kamil Deja, Kayoko Yanagisawa, Marius Cotescu

ICASSP 2023accepted

This work focuses on modelling a speaker’s accent that does not have a dedicated text-to-speech (TTS) frontend, including a grapheme-to-phoneme (G2P) module. Prior work on modelling accents assumes a phonetic transcription is available for the target accent, which might not be the case for low-resou…

Cited by 0 Source ↗Scholar ↗

2020

Using Vaes and Normalizing Flows for One-Shot Text-To-Speech Synthesis of Expressive Speech

Vatsal Aggarwal, Marius Cotescu, Nishant Prateek, Jaime Lorenzo-Trueba, Roberto Barra-Chicote

ICASSP 2020accepted

We propose a Text-to-Speech method to create an unseen expressive style using one utterance of expressive speech of around one second. Specifically, we enhance the disentanglement capabilities of a state-of-the-art sequence-to-sequence based system with a Variational AutoEncoder (VAE) and a Househol…

Cited by 0 Source ↗Scholar ↗