Picture for Edresson Casanova

Edresson Casanova

XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model

Add code
Jun 07, 2024
Viaarxiv icon

MLAAD: The Multi-Language Audio Anti-Spoofing Dataset

Jan 17, 2024
Viaarxiv icon

Evaluation of Speech Representations for MOS prediction

Add code
Jun 16, 2023
Figure 1 for Evaluation of Speech Representations for MOS prediction
Figure 2 for Evaluation of Speech Representations for MOS prediction
Figure 3 for Evaluation of Speech Representations for MOS prediction
Figure 4 for Evaluation of Speech Representations for MOS prediction
Viaarxiv icon

CML-TTS A Multilingual Dataset for Speech Synthesis in Low-Resource Languages

Add code
Jun 16, 2023
Viaarxiv icon

Evaluating OpenAI's Whisper ASR for Punctuation Prediction and Topic Modeling of life histories of the Museum of the Person

Add code
May 26, 2023
Figure 1 for Evaluating OpenAI's Whisper ASR for Punctuation Prediction and Topic Modeling of life histories of the Museum of the Person
Figure 2 for Evaluating OpenAI's Whisper ASR for Punctuation Prediction and Topic Modeling of life histories of the Museum of the Person
Viaarxiv icon

Interpretability Analysis of Deep Models for COVID-19 Detection

Nov 25, 2022
Figure 1 for Interpretability Analysis of Deep Models for COVID-19 Detection
Figure 2 for Interpretability Analysis of Deep Models for COVID-19 Detection
Figure 3 for Interpretability Analysis of Deep Models for COVID-19 Detection
Figure 4 for Interpretability Analysis of Deep Models for COVID-19 Detection
Viaarxiv icon

BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus

Add code
Jul 07, 2022
Figure 1 for BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus
Figure 2 for BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus
Figure 3 for BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus
Figure 4 for BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus
Viaarxiv icon

A single speaker is almost all you need for automatic speech recognition

Add code
Mar 29, 2022
Figure 1 for A single speaker is almost all you need for automatic speech recognition
Figure 2 for A single speaker is almost all you need for automatic speech recognition
Figure 3 for A single speaker is almost all you need for automatic speech recognition
Viaarxiv icon

YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone

Add code
Dec 04, 2021
Figure 1 for YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone
Figure 2 for YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone
Figure 3 for YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone
Figure 4 for YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone
Viaarxiv icon

CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese

Add code
Oct 14, 2021
Figure 1 for CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese
Figure 2 for CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese
Figure 3 for CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese
Figure 4 for CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese
Viaarxiv icon