Picture for Sewade Ogun

Sewade Ogun

Performant ASR Models for Medical Entities in Accented Speech

Jun 18, 2024
Viaarxiv icon

1000 African Voices: Advancing inclusive multi-speaker multi-accent speech synthesis

Add code
Jun 17, 2024
Viaarxiv icon

Stochastic Pitch Prediction Improves the Diversity and Naturalness of Speech in Glow-TTS

Add code
May 28, 2023
Figure 1 for Stochastic Pitch Prediction Improves the Diversity and Naturalness of Speech in Glow-TTS
Figure 2 for Stochastic Pitch Prediction Improves the Diversity and Naturalness of Speech in Glow-TTS
Figure 3 for Stochastic Pitch Prediction Improves the Diversity and Naturalness of Speech in Glow-TTS
Viaarxiv icon

Can we use Common Voice to train a Multi-Speaker TTS system?

Add code
Oct 12, 2022
Figure 1 for Can we use Common Voice to train a Multi-Speaker TTS system?
Figure 2 for Can we use Common Voice to train a Multi-Speaker TTS system?
Figure 3 for Can we use Common Voice to train a Multi-Speaker TTS system?
Figure 4 for Can we use Common Voice to train a Multi-Speaker TTS system?
Viaarxiv icon