audEERING is creator and owner of the world-class audio analysis toolkit openSMILE. This software is applied in many scientific and academic projects.
GET STARTED WITH AUDIO ANALYSIS
OUR OPEN SOURCE SOLUTION
It is a widely used feature extraction and pattern recognition tool which is applied for a large variety of different usecases. More details and a free trial version of openSMILE are available as download here.
SMILE is an acronym for speech and music interpretation by large-space extraction. The openSMILE feature extration tool enables you to extract large audio feature spaces in real time. It combines features from Music Information Retrieval and Speech Processing. Written in C++ the feature extractor components can be freely interconnected to create new and custom features, all via a simple configuration file. New components can be added to openSMILE via an easy binary plugin interface and a comprehensive API.
Can anyone use openSMILE?
If you use openSMILE in your research, please cite the following paper for version 2.x and above:
Florian Eyben, Felix Weninger, Florian Gross, Björn Schuller: “Recent Developments in openSMILE, the Munich Open-Source Multimedia Feature Extractor”, In Proc. ACM Multimedia (MM), Barcelona, Spain, ACM, ISBN 978-1-4503-2404-5, pp. 835-838, October 2013. doi:10.1145/2502081.2502224
For older work based on openSMILE version 1.0.1 and below, you may cite this paper:
Florian Eyben, Martin Wöllmer, Björn Schuller: “openSMILE – The Munich Versatile and Fast Open-Source Audio Feature Extractor”, In Proc. ACM Multimedia (MM), ACM, Florence, Italy, ACM, ISBN 978-1-60558-933-6, pp. 1459-1462, October 2010. doi:10.1145/1873951.1874246
We are always happy to hear what people are using openSMILE for. Thus, we would appreciate it, if you would send us a brief note with a reference to your paper, and/or a brief description of your work.
Installation and Documentation
openSMILE’s architecture and usage is well documented in the openSMILE book (available electronically as PDF). The book is included with every release in the doc/ folder.
For version 2.1, we have published an additional tutorial in ACM SIGMM records.
Detailed and extensive theoretical descriptions of the implemented algorithms and concepts can be found in Florian Eyben’s doctoral thesis “Real-time Speech and Music Classification by Large Audio Feature Space Extraction” available at Springer. This is a must-have book for everyone who works with openSMILE and wants to get more insight into the theoretical descriptions of the feature extraction algorithms.
Full Installation and usage instructions are provided in the book. Here are quick-Install instructions for the impatient:
- Run from a binary release: look for a suitable SMILExtract* binary (linux) or SMILExtract*.exe (Windows) in the bin/ subdirectory of the release package and run it from the command line with the -h option to see an on-line help.
- Build the core from source on Linux: run the script buildStandalone.sh (requires automake and autoconf and build-essentials – gcc, g++, make, libtool – to be installed),
- Build the core from source on Windows in Visual Studio (2010 or higher with conversion of project files): open the openSMILE.slnsolutions in the folder ide/vs10 and build the full solution (you might have to build several times because Visual Studio does not automatically get all the dependencies between the projects in the solutions).
- Compiling with Portaudio support: Please read the openSMILE book
Download and Releases
The brand new release of openSMILE 2.3 is now available (Oct. 28th 2016). It can be downloaded using the links above. Version 2.3 includes Android JNI integration, an updated configuration file interface, a batch feature extraction GUI for Windows, improved backwards compatibility, an updated version of the ComParE 2013-2015 baseline acoustic parameter set, as well as several bugfixes and performance improvements.
To have access to older releases you may contact us.
AUDIO INTELLIGENCE BY audEERING
openSMILE is used in many research projects
openSMILE is used in many of audEERING’s projects, which are funded by the German government and the EU. Among others, audEERING is a partner within several governmental projects funded by the European Comission and the German Federal Ministry of Education and Research (BMBF).