Picture for Anton Ragni

Anton Ragni

What happens to diffusion model likelihood when your model is conditional?

Add code
Sep 10, 2024
Viaarxiv icon

Foundation Models for Music: A Survey

Add code
Aug 27, 2024
Viaarxiv icon

Self-Train Before You Transcribe

Add code
Jun 17, 2024
Viaarxiv icon

Training Data Augmentation for Dysarthric Automatic Speech Recognition by Text-to-Dysarthric-Speech Synthesis

Add code
Jun 12, 2024
Viaarxiv icon

Non-Intrusive Speech Intelligibility Prediction for Hearing-Impaired Users using Intermediate ASR Features and Human Memory Models

Add code
Jan 24, 2024
Viaarxiv icon

How Much Context Does My Attention-Based ASR System Need?

Add code
Oct 24, 2023
Viaarxiv icon

Energy-Based Models For Speech Synthesis

Add code
Oct 19, 2023
Viaarxiv icon

MARBLE: Music Audio Representation Benchmark for Universal Evaluation

Add code
Jul 12, 2023
Viaarxiv icon

On the Effectiveness of Speech Self-supervised Learning for Music

Add code
Jul 11, 2023
Viaarxiv icon

Leveraging Cross-Utterance Context For ASR Decoding

Add code
Jun 29, 2023
Viaarxiv icon