Picture for Matteo Negri

Matteo Negri

MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages

Add code
Oct 01, 2024
Figure 1 for MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages
Figure 2 for MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages
Figure 3 for MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages
Figure 4 for MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages
Viaarxiv icon

What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Study

Add code
Oct 01, 2024
Viaarxiv icon

Self-attention as an attractor network: transient memories without backpropagation

Add code
Sep 24, 2024
Viaarxiv icon

Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond

Add code
Aug 07, 2024
Viaarxiv icon

Random Features Hopfield Networks generalize retrieval to previously unseen examples

Add code
Jul 08, 2024
Viaarxiv icon

SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation

Add code
Jun 20, 2024
Viaarxiv icon

StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection

Add code
Jun 10, 2024
Viaarxiv icon

Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentation

Add code
Jun 06, 2024
Figure 1 for Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentation
Figure 2 for Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentation
Figure 3 for Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentation
Figure 4 for Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentation
Viaarxiv icon

SBAAM! Eliminating Transcript Dependency in Automatic Subtitling

Add code
May 17, 2024
Viaarxiv icon

Enhancing Gender-Inclusive Machine Translation with Neomorphemes and Large Language Models

Add code
May 14, 2024
Viaarxiv icon