Module I: Speech Technologies

Within the course, students familiarize themselves with the development and application of intelligent audio and speech systems. Fundamental aspects of human auditory perception are covered, along with basic methods for the analysis and synthesis of speech and other sound signals.  

The course addresses methods for preprocessing and analyzing the characteristics of captured sound signals, enabling the recognition of distinctive sounds such as various environmental sounds, animal sounds, and traffic sounds. Attention is also given to the possibility of sound analysis for verifying the operation of machines and devices and for diagnosing their malfunctions.

Special emphasis is placed on systems for speech and speaker recognition and on the statistical modeling of spoken languages. Systems for generating synthetic speech and human-machine communication systems are also discussed, including dialogue management systems, models for representing knowledge in such systems, and multimodality in communication. 

The aim of this course is to acquaint students with the field of machine hearing and speech technologies and to introduce various algorithms, techniques, and methods to accomplish different tasks related to field of the course. 

Lectures, Interactive teaching, Practical assignments, Seminar work.