Profile
Our group focuses on research, development and implementation of advanced digital signal processing algorithms, mainly in the fields of adaptive control and audio processing. We build on our experience with statistics, namely with the Bayesian approach to system identification and modeling, as well as the relevant fields of linear algebra.
Our target platforms are Field Programmable Gate Arrays (FPGAs) and Digital Signal Processors (DSPs). We use Matlab/Simulink to specify, model and verify algorithms that we later convert and synthesize to HW. As such specialized solutions are likely to be used in embedded systems, we also research features that result in extremely fast execution, use small amount of memory, small chip area or low power consumption. We achieve this both through designing new or modifying existing DSP algorithms, and using architectural properties such as dynamic reconfiguration of FPGAs...
News
Embedded World 2025
Embedded World 2025 Exhibition & Conference took place in Nuremberg from 11– 13 March 2025. We had an opportunity to present the demonstrators developed in SOIL, Listen2Future and StorAIge projects at TRENZ Electronic booth (Hall 5 / Booth Number 5-140). See some photos from this event.
EFECS 2024
EFECS 2024 – Strengthening EU competitiveness European Forum for Electronic Components and Systems took place in Ghent, Belgium, on December 5-6, 2024. We had the opportunity to present our demonstrator AI self-trained, ulrasound-based, hand gesture recognition at StorAIge project booth. We also presented the Ultra-sound beamformer demonstrator at Listen2Future project booth. See photos from this event.
SOIL Project
The EU research project SOIL has started 1 June 2024. The project is financed by investments from industry, subsidies from the individual participating countries and the Chips JU programme. Our group develops ultrasound sensor of electric discharges on power distribution lines. We develop ultrasound beamformer working with circular microphone phase array of 32 ultrasound microphones.
StorAIge use case: AI self-trained, ultrasound-based, hand gesture recognition
In the frame of StorAIge project our group developed the use case AI self-trained, ultrasound-based, hand gesture recognition. This use case fits to the Gesture recognition application field.
StorAIge 2nd Review Meeting
The 2nd Review meeting of StorAIge project was held at STMicroelectronics in Crolles, France, 10th -11th October 2023. During the session devoted to StorAIge's live demonstrators, our colleague Jiri Kadlec presented UTIA implementation of HW accelerated AI pose-detection algorithm with full HD HDMI camera input. See …
Listen2Future WP7 Podcast recordings
First episode of the Listen2Future Podcast has been launched on the website, the social media channels (LinkedIn, Twitter, Facebook) and Spotify.