Computational Auditory Scene Analysis

Analysis of acoustic environments for audition research

Experience the live demos of inhouse developed, state of the art deep learning based models for Robot Audition. Focused areas are on the topics of Acoustic Scene Classification (ASC), Sound Event Localization & Detection (SELD) and Automated Audio Captioning (AAC).


Acoustic Scene Classification

Classification of recording files and real time audio into one of the predefined acoustic scene classes


Sound Event Localization and Detection

Spatio-temporal characterization of the acoustic scene for wide range of machine cognition tasks


Automated Audio Captioning

An intermodal translation task of general audio content description using free text