Archontis Politis
About me
I am an assistant professor in audio signal processing and machine learning at the Faculty of Information Technology and Communication Sciences of Tampere University, and part of the Audio Research Group and the Signal Processing Research Center.
Responsibilities
Apart from research and teaching at Tampere University, I am additionally a member of the European Association for Signal Processing (EURASIP) technical area committee on Acoustic, Speech, and Music Signal Processing, and a regular organiser in the DCASE Challenge. On the industry side, I am a co-founder of Aani, a spatial audio technology startup.
Fields of expertise
My research focus is on capturing, modeling, and rendering spatial properties of sound scenes using both signal processing and machine learning methods. Applications of the research range from 3D audio capture, spatial audio coding, spatial audio rendering, and audio for XR, to sound source localization and tracking, acoustic SLAM, and spatial machine listening. I am additionally interested in sound field modeling, virtual acoustics, and acoustical modeling in general.
Top achievements
Some personal milestones that I believe had/have some real-world impact to the research community in academia and industry:
- Editor of "Parametric Time-Frequency Domain Spatial Audio", Ville Pulkki, Symeon Delikaris-Manias, Archontis Politis, Wiley/IEEE Press, Dec. 2017.
- SPARTA/COMPASS advanced spatial audio production tools (with PhD supervisee Leo McCormack).
- Main organiser of Sound Event Localization and Detection task in DCASE Challenge, 2020-2024.
- Architect of the reference implementation of "6DOF spatial audio rendering from multi-point recordings" track in the MPEG-I standard for next-gen immersive media (together with Nokia Technologies).
Research unit
Latest publications
Attractor-Based Speech Separation of Multiple Utterances by Unknown Number of Speakers
Wang, Y., Politis, A., Drossos, K. & Virtanen, T., 2025, Interspeech 2025. ISCA, p. 1453-1457 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
Class-Incremental Learning for Sound Event Localization and Detection
Pandey, R., Mulimani, M., Politis, A. & Mesaros, A., 2025, 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW). IEEE, p. 1-5 (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
Gen-A: Generalizing Ambisonics Neural Encoding to Unseen Microphone Arrays
Heikkinen, M., Politis, A., Drossos, K. & Virtanen, T., 2025, ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Rao, B. D., Trancoso, I., Sharma, G. & Mehta, N. B. (eds.). IEEE, p. 1-5 (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
Inter-Speaker Relative Cues for Text-Guided Target Speech Extraction
Dai, W., Politis, A. & Virtanen, T., 2025, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. ISCA, p. 1918-1922 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
Learning Order Matters in Class-Incremental Learning for Sound Localization and Detection
Pandey, R., Mulimani, M., Politis, A. & Mesaros, A., 2025, 2025 33rd European Signal Processing Conference (EUSIPCO). IEEE, p. 251-255Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
Multi-Utterance Speech Separation and Association Trained on Short Segments
Wang, Y., Politis, A., Drossos, K. & Virtanen, T., 2025, 2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA). IEEE, p. 1-5 (IEEE Workshop on Applications of Signal Processing to Audio and Acoustics).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
Score-Informed Music Source Separation: Improving Synthetic-To-Real Generalization in Classical Music
Eetu, T., Diaz-Guerra Aparicio, D., Politis, A. & Virtanen, T., 17 Nov 2025, 2025 33rd European Signal Processing Conference (EUSIPCO): Proceedings. IEEE, p. 1238 1242 p.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
Stereo Sound Event Localization and Detection with Onscreen/offscreen Classification
Shimada, K., Politis, A., Roman, I. R., Ariyakulam Sudarsanam, P., Diaz-Guerra Aparicio, D., Pandey, R., Uchida, K., Koyama, Y., Takahashi, N., Shibuya, T., Takahashi, S., Virtanen, T. & Mitsufuji, Y., Oct 2025, Proceedings of the 10th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2025). DCASE, p. 140-144 4 p.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
SynthSOD: Developing an Heterogeneous Dataset for Orchestra Music Source Separation
Garcia-Martinez, J., Diaz-Guerra, D., Politis, A., Virtanen, T., Carabias-Orti, J. J. & Vera-Candeas, P., 2025, In: IEEE Open Journal of Signal Processing. 6, p. 129-137Research output: Contribution to journal › Article › Scientific › peer-review
A Dataset for Location- and Direction-Dependent Reverberation Analysis
Alary, B. & Politis, A., 2024, Proceedings of the 10th Convention of the European Acoustics Association Forum Acusticum 2023. European Acoustics Association, p. 1663-1670 (Proceedings of Forum Acusticum).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review