Picture for Mircea Giurgiu

Mircea Giurgiu

An objective evaluation of the effects of recording conditions and speaker characteristics in multi-speaker deep neural speech synthesis

Add code
Jun 03, 2021
Figure 1 for An objective evaluation of the effects of recording conditions and speaker characteristics in multi-speaker deep neural speech synthesis
Figure 2 for An objective evaluation of the effects of recording conditions and speaker characteristics in multi-speaker deep neural speech synthesis
Figure 3 for An objective evaluation of the effects of recording conditions and speaker characteristics in multi-speaker deep neural speech synthesis
Figure 4 for An objective evaluation of the effects of recording conditions and speaker characteristics in multi-speaker deep neural speech synthesis
Viaarxiv icon

Speaker verification-derived loss and data augmentation for DNN-based multispeaker speech synthesis

Add code
Jun 03, 2021
Figure 1 for Speaker verification-derived loss and data augmentation for DNN-based multispeaker speech synthesis
Figure 2 for Speaker verification-derived loss and data augmentation for DNN-based multispeaker speech synthesis
Figure 3 for Speaker verification-derived loss and data augmentation for DNN-based multispeaker speech synthesis
Figure 4 for Speaker verification-derived loss and data augmentation for DNN-based multispeaker speech synthesis
Viaarxiv icon