Annamaria Mesaros
About me
My research area is Machine Listening, with focus on Detection and Classification of Acoustic Scenes and Events. My work includes different environmental sound detection and classification tasks, data collection and annotation procedures, evaluation methodology and metrics. I have been actively involved into promoting DCASE Challenge and Workshop , both through coordination work and publication of open data and research.
Responsibilities
I am the leader of the Machine Listening Group. On the group webpage you can find detailed informaiton about the group members, research topics, and the list of publications with links to (green) open access for all of them.
Latest publications
Binaural Sound Source Distance Estimation and Localization for a Moving Listener
Krause, D. A., Garcia-Barrios, G., Politis, A. & Mesaros, A., 2024, In: IEEE/ACM Transactions on Audio Speech and Language Processing. 32, p. 996 - 1011 16 p.Research output: Contribution to journal › Article › Scientific › peer-review
Aggregate or Separate: Learning From Multi-Annotator Noisy Labels for Best Classification Performance
Martín-Morató, I., Ahokas, P. & Mesaros, A., 2023, Proceedings of the 8th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2023). Fuentes, M., Heittola, T., Imoto, K., Mesaros, A., Politis, A., Serizel, R. & Virtanen, T. (eds.). p. 106-110Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
Evaluating Classification Systems Against Soft Labels with Fuzzy Precision and Recall
Harju, M. & Mesaros, A., 2023, Proceedings of the 8th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2023). Fuentes, M., Heittola, T., Imoto, K., Mesaros, A., Politis, A., Serizel, R. & Virtanen, T. (eds.). p. 46-50Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
Incremental Learning of Acoustic Scenes and Sound Events
Mulimani, M. & Mesaros, A., 2023, Proceedings of the 8th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2023). Fuentes, M., Heittola, T., Imoto, K., Mesaros, A., Politis, A., Serizel, R. & Virtanen, T. (eds.). p. 131-135Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
Proceedings of the 8th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2023)
Fuentes, M. (ed.), Heittola, T. (ed.), Imoto, K. (ed.), Mesaros, A. (ed.), Politis, A. (ed.), Serizel, R. (ed.) & Virtanen, T. (ed.), 2023, 235 p.Research output: Book/Report › Anthology › Scientific › peer-review
Self-Supervised Learning of Audio Representations using Angular Contrastive Loss
Wang, S., Tripathy, S. & Mesaros, A., 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings. IEEE, (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; vol. 2023-June).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
Sound Event Classification with Object-Based Labels
Afolaranmi, J., Martín-Morató, I. & Mesaros, A., 2023, Proceedings of the 8th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2023). Fuentes, M., Heittola, T., Imoto, K., Mesaros, A., Politis, A., Serizel, R. & Virtanen, T. (eds.). p. 1-5Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
Strong labeling of sound events using crowdsourced weak labels and annotator competence estimation
Martin-Morato, I. & Mesaros, A., 2023, In: IEEE/ACM Transactions on Audio Speech and Language Processing. 31, p. 902-914 13 p.Research output: Contribution to journal › Article › Scientific › peer-review
Training Sound Event Detection with Soft Labels from Crowdsourced Annotations
Martin Morato, I., Harju, M., Ahokas, P. & Mesaros, A., 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, (Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
A summarization approach to evaluating audio captioning
Martin Morato, I., Harju, M. & Mesaros, A., 3 Nov 2022, Proceedings of the 7th Workshop on Detection and Classication of Acoustic Scenes and Events (DCASE 2022). Lagrange, M., Mesaros, A., Pellegrini, T., Richard, G., Serizel, R. & Stowell, D. (eds.). p. 116-120Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review