Audio laboratory is used for analysis and processing of audio signals. Its space and infrastructure serves for the needs of speech and audio signal processing. The projects solved here create a base for TTS (text-to-speech) synthesis based on a high-quality speech databases. Moreover, in the laboratory is done the research in the area of prosody and emotions modification of the speech, then in the area of speech recognition, and psychoacoustic measurements focused on speech recognition and speech synthesis. The laboratory is covered by acoustic absorption materials. It contains the necessary equipment for recording, analysis and digital processing of audio and speech signals.
The main focus of the laboratory is recording of high-quality corpus databases and databases for measuring of prosodic parameters in the speech. It is also focused on recording of domain-oriented databases for TTS systems that extendable to multilingual databases, as well as to recording domain-oriented sinusoidal databases for TTS, speech recognition and voice identification systems. The laboratory is also used in research on Slovak language prosody modification and on statistical measurement and prosody evaluation in sentences, and is used in research on emotions modification in the Slovak speech. The next research is done on low bitrate of speech coding / compression methods using TTS synthesis in mobile phones, and on voice conversion, speech recognition and psychoacoustics research.
Laboratory and software systems are also used in the teaching activities at the Department of Telecommunications - for diploma and bachelor theses and for student team works, as well as for students who are attending subjects Digital Speech Processing and Digital Signal Processing.
