Skip to main content
Tampere University
annamaria.mesaros [at] tuni.fi (annamaria[dot]mesaros[at]tuni[dot]fi)
phone number+358504799943

About me

My research area is computational audio content analysis with a focus on Machine Listening. This includes different environmental sound detection and classification tasks, audio captioning, continual learning for audio, audio data collection and annotation procedures, evaluation methodology for related task, and metrics. 

I am actively involved in the DCASE Challenge as a task organizer and general challenge coordinator. I am also the vice-chair of the DCASE Community and a regular contributor to the DCASE workshop as an author and reviewer. 

I am a member of ELLIS Society, Climate AI Nordics, IEEE AASP Technical committee, and EURASIP ASMSP TAC

Responsibilities

I am the leader of the Machine Listening Group. On the group webpage you can find detailed information about the current group members, active research topics, and the complete list of our publications with links to (green) open access for all of them. 

During academic year 2024-2025 I am teaching the Advanced Audio Processing course.  

Research topics

Sound event detection

Acoustic scene and sound event classification

Audio-visual feature learning

Audio captioning

Continual learning for audio

Research fields

Computational audio content analysis, Audio signal processing, Machine listening, Machine learning for audio

Latest publications