Picture for Bartosz Putrycz

Bartosz Putrycz

BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data

Add code
Feb 15, 2024
Viaarxiv icon

Enhancing audio quality for expressive Neural Text-to-Speech

Add code
Aug 13, 2021
Figure 1 for Enhancing audio quality for expressive Neural Text-to-Speech
Figure 2 for Enhancing audio quality for expressive Neural Text-to-Speech
Figure 3 for Enhancing audio quality for expressive Neural Text-to-Speech
Figure 4 for Enhancing audio quality for expressive Neural Text-to-Speech
Viaarxiv icon

Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech

Add code
Jun 25, 2021
Figure 1 for Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech
Figure 2 for Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech
Figure 3 for Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech
Figure 4 for Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech
Viaarxiv icon

Universal Neural Vocoding with Parallel WaveNet

Add code
Feb 15, 2021
Figure 1 for Universal Neural Vocoding with Parallel WaveNet
Figure 2 for Universal Neural Vocoding with Parallel WaveNet
Figure 3 for Universal Neural Vocoding with Parallel WaveNet
Figure 4 for Universal Neural Vocoding with Parallel WaveNet
Viaarxiv icon