Around half of the information humans exchange during interaction is not the meaning of speech itself. Speech audio signal carries information about the age, gender, emotion of the speaker. In this talk we will discuss the information that can be obtained from the speech signal, potential approaches and applications. Then we will extend the scope with extracting information from non-speech audio – audio events detection and audio background recognition. We will discuss the technologies and algorithms for solving these problems – neural networks with supervised and non-supervised training, most commonly used features and cost functions. Speaker(s): Dr. Ivan Tashev , Virtual: https://events.vtools.ieee.org/m/370590