Picture for Tuomas Virtanen

Tuomas Virtanen

Tampere University

SynthSOD: Developing an Heterogeneous Dataset for Orchestra Music Source Separation

Add code
Sep 17, 2024
Viaarxiv icon

Multi-label Zero-Shot Audio Classification with Temporal Attention

Add code
Aug 31, 2024
Viaarxiv icon

Noise-to-mask Ratio Loss for Deep Neural Network based Audio Watermarking

Add code
Aug 28, 2024
Viaarxiv icon

Integrating Continuous and Binary Relevances in Audio-Text Relevance Learning

Add code
Aug 27, 2024
Viaarxiv icon

Computer Audition: From Task-Specific Machine Learning to Foundation Models

Add code
Jul 22, 2024
Viaarxiv icon

Reference Channel Selection by Multi-Channel Masking for End-to-End Multi-Channel Speech Enhancement

Add code
Jun 05, 2024
Viaarxiv icon

Speaker Distance Estimation in Enclosures from Single-Channel Audio

Add code
Mar 26, 2024
Viaarxiv icon

From Weak to Strong Sound Event Labels using Adaptive Change-Point Detection and Active Learning

Add code
Mar 13, 2024
Viaarxiv icon

Neural Ambisonics encoding for compact irregular microphone arrays

Add code
Jan 11, 2024
Viaarxiv icon

Attention-Driven Multichannel Speech Enhancement in Moving Sound Source Scenarios

Add code
Dec 17, 2023
Viaarxiv icon