Picture for Hagai Aronowitz

Hagai Aronowitz

Continuous Speech Synthesis using per-token Latent Diffusion

Add code
Oct 21, 2024
Viaarxiv icon

Extending RNN-T-based speech recognition systems with emotion and language classification

Add code
Jul 28, 2022
Figure 1 for Extending RNN-T-based speech recognition systems with emotion and language classification
Figure 2 for Extending RNN-T-based speech recognition systems with emotion and language classification
Figure 3 for Extending RNN-T-based speech recognition systems with emotion and language classification
Figure 4 for Extending RNN-T-based speech recognition systems with emotion and language classification
Viaarxiv icon

Towards a Common Speech Analysis Engine

Add code
Mar 01, 2022
Figure 1 for Towards a Common Speech Analysis Engine
Figure 2 for Towards a Common Speech Analysis Engine
Figure 3 for Towards a Common Speech Analysis Engine
Figure 4 for Towards a Common Speech Analysis Engine
Viaarxiv icon

Speech Emotion Recognition using Self-Supervised Features

Add code
Feb 07, 2022
Figure 1 for Speech Emotion Recognition using Self-Supervised Features
Figure 2 for Speech Emotion Recognition using Self-Supervised Features
Figure 3 for Speech Emotion Recognition using Self-Supervised Features
Figure 4 for Speech Emotion Recognition using Self-Supervised Features
Viaarxiv icon

Speaker Normalization for Self-supervised Speech Emotion Recognition

Add code
Feb 02, 2022
Figure 1 for Speaker Normalization for Self-supervised Speech Emotion Recognition
Figure 2 for Speaker Normalization for Self-supervised Speech Emotion Recognition
Figure 3 for Speaker Normalization for Self-supervised Speech Emotion Recognition
Viaarxiv icon

Siamese x-vector reconstruction for domain adapted speaker recognition

Add code
Jul 28, 2020
Figure 1 for Siamese x-vector reconstruction for domain adapted speaker recognition
Figure 2 for Siamese x-vector reconstruction for domain adapted speaker recognition
Figure 3 for Siamese x-vector reconstruction for domain adapted speaker recognition
Figure 4 for Siamese x-vector reconstruction for domain adapted speaker recognition
Viaarxiv icon