AILab

AILab@TUL deals with research and application of machine learning methods for processing of speech, image, and text data. In speech, this is mainly the task of automatic transcription, speaker diarization, or language identification from acoustic signals. In the context of image processing, the lab is primarily specialized in methods for object or person detection. In text processing, the researchers exploit extensive pre-trained language models, for example, in the task of automatic punctuation completion, word capitalization, or anonymization of text documents.

AILab was founded as Speechlab in 1994 by prof. Jan Nouza who has been working in the field of speech processing since his university studies in 1980s. Since then it has been one of the leading labs in the field of voice technologies in the Czech Republic.

The laboratory aims to conduct world-class research with practical applicability and significant social impact. Examples of such work include creating a recognition engine and models for the following services. Newton Dictate is a software for real-time continuous dictation. The Beey web service allows the creation of transcription/subtitles and their correction in many European languages. The MyDictate and MyVoice programs developed by AILab allow disabled people to control the computer by voice or to dictate text word by word.