Picture for Eduardo Lleida

Eduardo Lleida

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

Add code
Sep 09, 2024
Viaarxiv icon

Defining and Measuring Disentanglement for non-Independent Factors of Variation

Add code
Aug 13, 2024
Viaarxiv icon

Predefined Prototypes for Intra-Class Separation and Disentanglement

Add code
Jun 23, 2024
Viaarxiv icon

Improved Vocal Effort Transfer Vector Estimation for Vocal Effort-Robust Speaker Verification

Add code
May 03, 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

Shouted Speech Compensation for Speaker Verification Robust to Vocal Effort Conditions

Add code
Aug 06, 2020
Figure 1 for Shouted Speech Compensation for Speaker Verification Robust to Vocal Effort Conditions
Figure 2 for Shouted Speech Compensation for Speaker Verification Robust to Vocal Effort Conditions
Figure 3 for Shouted Speech Compensation for Speaker Verification Robust to Vocal Effort Conditions
Figure 4 for Shouted Speech Compensation for Speaker Verification Robust to Vocal Effort Conditions
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

Tied Hidden Factors in Neural Networks for End-to-End Speaker Recognition

Add code
Dec 27, 2018
Figure 1 for Tied Hidden Factors in Neural Networks for End-to-End Speaker Recognition
Figure 2 for Tied Hidden Factors in Neural Networks for End-to-End Speaker Recognition
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