Welcome to the documentation of openSMILE (open-Source Media Interpretation by Large feature-space Extraction).

openSMILE allows you to extract audio and video features for signal processing and machine learning, with an emphasis on features enabling emotion recognition from speech.

The official openSMILE homepage can be found at:

To obtain binaries, source code and report issues, visit the openSMILE page on GitHub:

Original authors: Florian Eyben, Felix Weninger, Martin Wöllmer, Björn Schuller
E-mails: fe, fw, mw, bs at
D-82205 Gilching, Germany