Work

Blizzard Challenge 2027: Accented Zero-Shot TTS in Spontaneous Portuguese Speech (Training Material)

Year: 2026

Type: article

Abstract: This report details the training material for the Blizzard Challenge 2027, which focuses on accented zero-shot Text-to-Speech (TTS) in spontaneous Portuguese. We describe three primary datasets: NURC-SP (São Paulo), NURC-RE (Recife), and FalAR-TTS (European Portuguese). More Info: https://nilc-nlp.github.io/ssw-2027/blizzard-challenge-dates.html and https://nilc-nlp.github.io/ssw-2027/blizzard-challenge-rules.html

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.20975208

Authors: Leal, Sidney Evaldo, Paulo, Sérgio, Abad, Alberto, Fernandes-Svartman, Flaviane, Quadros Leite, Marli, Oliveira, Jr., Miguel

Institutions: Universidade de São Paulo, Instituto Superior Técnico, Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento, Universidade Federal de Alagoas

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7166305845

FWCI:

Cites:

Cited by:

Related to: