Archives

We are very happy to welcome 3 new Ph.D. students admitted to the AGH Doctoral School, who will be associated with the Signal Processing Group. Mgr inż. Julitta Bartolewska and mgr inż. Mieszko Fraś will join the APDAS project at Ph.D. positions, while mgr inż. Mateusz Guzik will take the Ph.D. position in the MLSAP […]

Associate Professor Konrad Kowalczyk will give a lecture entitled “Voice-based interfaces – state of the art and future challenges” at an inauguration of the academic year at the Faculty of Computer Science, Electronics and Telecommunication, AGH University of Science and Technology. Inauguration takes place on October the 2nd, 2020 at 9:00 and will be transmitted […]

We are pleased to congratulate Dr Magdalena Cybulska-Igras on receiving funding from The National Centre for Research and Development (NCBR) for her project entitled “glossoVR 2.0 – virtual trainer of voice emission and public speaking”. The project proposal was submitted within the Lider program which supports young Polish researchers to lead their first R&D project. […]

The DSP AGH team consisting of Magdalena Rybicka, Stanisław Kacprzak, Marcin Witkowski and Konrad Kowalczyk participated in the Short-duration Speaker Verification (SdSV) Challenge organized as a satellite event of the INTERSPEECH 2020 conference. The DSP team competed in Task2: Text-independent Speaker Verification. The technical report and the challenge results have recently been announced by the […]

On June 11th, MSc student Julitta Bartolewska is giving a presentation at the 11th IEEE Sensor Array and Multichannel Signal Processing Workshop 2020. Instead of giving a life presentation in Hangzhou, China, Julitta will present the paper on “Distributed Multiarray Noise Reduction With Online Estimation Of Masks And Spatial Filters” at the Virtual Conference SAM […]

We would like to invite you to the Ph.D. defense of mgr inż. Stanisław Kacprzak on January the 14th 2020 which will take place in D17, Room 1.20 at 13:30. The Ph.D. thesis title is “Spoken language recognition in i-vector space using cluster based modeling“.

Photo taken after the final presentation of a visiting student Fukutani Kazuki.

It is our pleasure to welcome mgr inż. Magdalena Rybicka and mgr inż. Dawid Smoleń who have been admitted to AGH Doctoral School. Magda’s research will focus on speaker identification/recognition using deep neural network (DNN) based speaker embeddings, while Dawid will apply machine learning to timbre transfer.

Great thanks to Prof Tuomas Virtanen and Dr Archontis Politis for inviting our MSc student and MLSAP project member Daniel Krause to pay a month long research visit to the Audio Processing Group at Tampere University in Finland in summer of 2019, and a week long stay of Konrad Kowalczyk over the period. This visit […]