Edresson Casanova

机构：Nvidia (United Kingdom), Nvidia (United States) · ORCID：0000-0003-0160-7173

发表论文 71 篇 · 总被引 481 次 · h-index 10

代表论文

• XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model (2024 · 被引 121)
• MLAAD: The Multi-Language Audio Anti-Spoofing Dataset (2024 · 被引 66)
• CORAA ASR: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese (2022 · Language Resources and Evaluation · 被引 18)
• BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus (2022 · Interspeech 2022 · 被引 11)
• ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion (2023 · 被引 8)
• CML-TTS: A Multilingual Dataset for Speech Synthesis in Low-Resource Languages (2023 · Lecture notes in computer science · 被引 8)