AGH Signal Processing Group

The Signal Processing Group is part of the Institute of Electronics, which belongs to the Faculty of Computer Science, Electronics and Telecommunications at AGH University of Krakow, Poland. Group members perform research into various aspects of digital signal processing (DSP) focusing mainly on speech and audio signal processing for the Internet of Things (IoT), multimedia and communication applications, as well as the processing of biomedical signals and audio-video for virtual and augmented reality. Research into signal processing builds upon an intelligent integration of classical DSP techniques, statistical signal processing and machine learning. The Signal Processing Group is led by Associate Professor Konrad Kowalczyk and it consists of over a dozen of the members of academic staff and research students at a Ph.D. level. The DSP team collaborates internationally with renown academic partners (e.g. Johns Hopkins University, Tampere University, Brno University of Technology) and nationally with the local high-tech industry, and has successfully completed a number of research and commercial R&D projects. The group offers fundamental and advanced taught courses on signal processing, DSP, machine learning, and programming for embedded and multimedia applications at both undergraduate and graduate levels. The Signal Processing Group regularly offers student jobs in research and R&D projects, as well as provides a breadth of opportunities for thesis work and student internships. The Signal Processing Group expertise concentrates on application of advanced signal processing and machine learning to speech, audio, and biomedical signal processing. The group performs basic and applied research as well as provides consultancy and technology support for the industry. In the field of speech and audio signal processing, the group’s research is centered around communication, multimedia, Internet of Things, and virtual reality applications. The group develops intelligent voice enhancement for voice communication and human-computer interfaces (HCI) based on broad expertise in speech enhancement, noise reduction, dereverberation, multichannel signal extraction, signal quality restoration, and signal separation. Furthermore, our competencies include source localization from various microphone arrays and in distributed settings, applied among others in drone-based rescue. Over the years the group has built broad expertise in the analysis and processing of speech including speaker verification, diarization, language recognition, emotion recognition, speech synthesis and automatic speech recognition. In addition, our expertise concerns spatial audio processing, spatial sound rendering over headphones or loudspeakers, with applications ranging from home cinema, automotive, to virtual and augmented reality. In the context of the latter applications, the research interests concentrate on user experience when interacting with robots and virtual humans. The final research area is biomedical signal processing including EEG signal and image processing for medical applications. The Signal Processing Group welcomes opportunities from the industry to participate in R&D projects, provide consultancy and technology verification, licensing of developed technology, as well as support with implementation of signal processing in customer products. The group also welcomes research opportunities from international academic partners interested in co-operations and joint applications for research projects.

Audio & VR Lab

Speech Laboratory

Audio Processing using Distributed Acoustic Sensors (POIR.04.04.00-00-3FC4/17-00)

Machine learning in spatial audio processing (UMO-2017/25/B/ST7/01792)

Deep extraction for robust speech recognition (UMO-2021/42/E/ST7/00452)

Acoustic Intelligence - towards self-supervised deep neural acoustic analysis (UMO-2023/49/B/ST7/04100)

Intelligent voice assistant for managing medical records according to doctor recommendations (INFOSTRATEG4/0029/2022)

Center for Language and Speech Processing, Johns Hopkins University

Audio Research Group, Tampere University

Speech@FIT, Brno University of Technology

Multimedia and Signal Processing, University of Erlangen-Nuremberg

AudioLabs, Fraunhofer Institute

Aalto University, Helsinki

University of Valencia

Samsung Electronics