Cultural Heritage
Speech and Language Technologies (SALT)
Domains
Communication; Health and Accessibility; Industry 4.0; Smart Cities; Security; Cultural Heritage; Transportation and Aerospace
Technologies
speech recognition; speech synthesis; dialogue systems; natural language processing
Description
In the speech and language technologies group, we focus on research and development of advanced solutions related to voice-based human-computer communication. Characteristic examples include systems for automatic subtitling of television programs, multimodal and voice-based dialogue systems and chat applications, searching in extensive multimedia archives, or voice cloning technologies. During development, we employ the latest knowledge in the field of artificial intelligence (AI) and deep learning.
Computer Vision laboratory
Domains
Industry 4.0; Industrial Solutions; Infrastructures; Cultural Heritage, Health & Wellness, Smart Cities, Security, Transportation, Accessibility, Communication
Technologies
Robotics, Artificial Intelligence, Machine Learning, Large Language Models, Deep learning, Big Data, Neural Networks, Data mining, Edge Computing, Signal processing, Human-computer interaction, Computer Vision
Description
The Computer Vision (CV) lab focuses on the research and development of cutting-edge applications that utilize visual data—both images and video. Our work spans a variety of tasks, including image classification, object detection, optical character recognition (OCR), and quality assessment. While we employ classical computer vision techniques such as image preprocessing, segmentation, and morphological operations, our primary focus is on modern deep learning methods. We work with state-of-the-art neural network architectures, conducting training, evaluation, fine-tuning, and adapting these models to meet novel challenges and develop innovative solutions.