Archives

Our team member, mgr inż. Mateusz Guzik, participated in a 3-month PhD internship, during which he was working with the experts from Dolby in Barcelona, Spain. Together with the research staff from Dolby, mgr inż. Mateusz Guzik was working on deep learning approaches to spatial audio processing for beamforming applications. More information about the results […]

Traditionally, members of the Signal Processing group are present at Małopolska Noc Naukowców organized by the Faculty of Computer Science, Electronics and Telecommunication, AGH University of Krakow, which takes place on the 27th of September 2024. This year, visitors will hear about neural audio processing, try out a virtual medical assistant, and experience multimedia VR […]

We were very happy to host Alicja Misiuda from the University of Washington, Seattle over the summer at the Signal Processing group of AGH. Over the last 3 months Alicja was working under the supervision of dr inż. Stanisław Kacprzak on novel audio augmentation techniques, adapting methods known from image processing. More about the outcome […]

We are very pleased to inform that a journal article on diarization by Magdalena Rybicka in collaboration with partners from John Hopkins University has just been published on IEEE Xplore. Title: End-to-End Neural Speaker Diarization With Non-Autoregressive Attractors Authors: M. Rybicka, J. Villalba, T. Thebaud, N. Dehak and K. Kowalczyk Abstract: Despite many recent developments […]

We are happy to notify that a journal article by Mateusz Guzik on source separation from spatial Ambisonic signals has just been published on IEEE Xplore. You can find audio examples at Github. Title: On Ambisonic Source Separation With Spatially Informed Non-Negative Tensor Factorization Authors: Mateusz Guzik and Konrad Kowalczyk Abstract: This article presents a […]

We are happy to announce that an journal article by Mieszko Fraś on joint separation and dereverberation has just been published on IEEE Xplore. Title: Reverberant Source Separation Using NTF With Delayed Subsources and Spatial Priors Authors: Mieszko Fraś and Konrad Kowalczyk Abstract: Speech signals recorded by distant microphones are often contaminated with room reverberation […]

We pleased to announce that AGH’s Signal Processing Group obtained funding from the National Science Center (NCN) Poland under the OPUS program for the project entitled “Acoustic Intelligence – towards self-supervised deep neural acoustic analysis”. The principle investigator is associate professor Konrad Kowalczyk. More information can be found at AGH and IET Faculty.

Two members of AGH Signal Processing group, dr inż. Marcin Witkowski and mgr inż. Mateusz Guzik, spent 3 months over the summer on research visits to the esteemed international research groups. In both cases, these visits trigger new collaborations on speech and audio signal processing. Dr inż. Marcin Witkowski visited Speech@FIT research group at Brno […]