Picture for Victoria Mingote

Victoria Mingote

Audio-Visual Speaker Diarization: Current Databases, Approaches and Challenges

Add code
Sep 09, 2024
Viaarxiv icon

Direct Text to Speech Translation System using Acoustic Units

Add code
Sep 14, 2023
Viaarxiv icon

Improved Cross-Lingual Transfer Learning For Automatic Speech Translation

Add code
Jun 01, 2023
Viaarxiv icon

Class Token and Knowledge Distillation for Multi-head Self-Attention Speaker Verification Systems

Add code
Nov 06, 2021
Figure 1 for Class Token and Knowledge Distillation for Multi-head Self-Attention Speaker Verification Systems
Figure 2 for Class Token and Knowledge Distillation for Multi-head Self-Attention Speaker Verification Systems
Figure 3 for Class Token and Knowledge Distillation for Multi-head Self-Attention Speaker Verification Systems
Figure 4 for Class Token and Knowledge Distillation for Multi-head Self-Attention Speaker Verification Systems
Viaarxiv icon

Generalizing AUC Optimization to Multiclass Classification for Audio Segmentation With Limited Training Data

Add code
Oct 27, 2021
Figure 1 for Generalizing AUC Optimization to Multiclass Classification for Audio Segmentation With Limited Training Data
Figure 2 for Generalizing AUC Optimization to Multiclass Classification for Audio Segmentation With Limited Training Data
Figure 3 for Generalizing AUC Optimization to Multiclass Classification for Audio Segmentation With Limited Training Data
Viaarxiv icon

Optimization of the Area Under the ROC Curve using Neural Network Supervectors for Text-Dependent Speaker Verification

Add code
Jan 31, 2019
Figure 1 for Optimization of the Area Under the ROC Curve using Neural Network Supervectors for Text-Dependent Speaker Verification
Figure 2 for Optimization of the Area Under the ROC Curve using Neural Network Supervectors for Text-Dependent Speaker Verification
Figure 3 for Optimization of the Area Under the ROC Curve using Neural Network Supervectors for Text-Dependent Speaker Verification
Figure 4 for Optimization of the Area Under the ROC Curve using Neural Network Supervectors for Text-Dependent Speaker Verification
Viaarxiv icon

Differentiable Supervector Extraction for Encoding Speaker and Phrase Information in Text Dependent Speaker Verification

Add code
Dec 22, 2018
Figure 1 for Differentiable Supervector Extraction for Encoding Speaker and Phrase Information in Text Dependent Speaker Verification
Figure 2 for Differentiable Supervector Extraction for Encoding Speaker and Phrase Information in Text Dependent Speaker Verification
Figure 3 for Differentiable Supervector Extraction for Encoding Speaker and Phrase Information in Text Dependent Speaker Verification
Figure 4 for Differentiable Supervector Extraction for Encoding Speaker and Phrase Information in Text Dependent Speaker Verification
Viaarxiv icon