The openSMILE feature extration tool enables you to extract large audio feature spaces in realtime. It combines features from Music Information Retrieval and Speech Processing. SMILE is an acronym for Speech & Music Interpretation by Large-space Extraction. It is written in C++ and is available as both a standalone commandline executable as well as a dynamic library. The main features of openSMILE are its capability of on-line incremental processing and its modularity. 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.

A brief summary of openSMILE's features is given here (see the openSMILE book for a detailed description of the features):

• Cross-platform (Windows, Linux, Mac)
• Fast and efficient incremental processing in real-time
• High modularity and reusability of components
• Plugin support
• Multi-threading support for parallel feature extraction
  
• Audio I/O:
  
  • WAVE file reader/writer
  • Sound recording and playback via PortAudio library.
  • Acoustic echo cancellation for full duplex recording/playback in an open-microphone setting (via the Speex codec library)
• General audio signal processing:
  
  • Windowing Functions (Hamming, Hann, Gauss, Sine, ...)
  • Fast-Fourier Transform
  • Pre-emphasis filter
  • Comb filter (available soon)
  • FIR/IIR filter (available soon)
  • Autocorrelation
  • Cepstrum
• Extraction of speech-related features:
  
  • Signal energy
  • Loudness
  • Mel-/Bark-/Octave-spectra
  • MFCC
  • PLP-CC
  • Pitch
  • Voice quality
  • Formants
  • LPC
  • Line Spectral Pairs (LSP)
• Music-related features:
  
  • Pitch classes (semitone spectrum)
  • CHROMA and CENS features
  • Weighted differential
• Moving average smoothing of feature contours
• Moving average mean subtraction and variance normalisation (e.g. for on-line cepstral mean subtraction)
• On-line histogram equalisation (used for noise robust speech recognition)
• Delta Regression coefficients of arbitrary order
• Functionals:
  
  • Means, Extremes
  • Moments
  • Segments
  • Samples
  • Peaks
  • Linear and quadratic regression
  • Percentiles
  • Durations
  • Onsets
  • DCT coefficients
  • Zero-crossings
• Popular feature file formats are supported:
  
  • Hidden Markov Toolkit (HTK) parameter files (read/write)
  • WEKA Arff files (currently only non-sparse) (read/write)
  • Comma separated value (CSV) text (read/write)
  • LibSVM feature file format (write)
• Fully HTK compatible MFCC, PLP, energy, and delta regression coefficient computation
• Fast: 27k features can be extracted with an RTF of 0.08

[ top ]

openSMILE is free software distributed under the GPL license. Customised commercial licensing options are available from the authors upon request.

[ top ]

We provide a release package which contains the linux and windows binaries as well as the source code and example configurations. A .zip file is provided for Windows systems and a .tar.gz file for Unix systems (the contents of both files are the same, however). The latest version is available for download from sourceforge here.

The latest version is 1.0.1, released March 23rd 2010. This is a bugfix release.

The most up-to date code can be obtained from the Subversion repository. To get this code, type the following command in a command-line prompt on a system where SVN (http://subversion.tigris.org) is installed:

   svn co https://opensmile.svn.sourceforge.net/svnroot/opensmile/trunk opensmile

openSMILE is well documented in the openSMILE book, which is available in electronic form as PDF. It is included with every release version, and can be also downloaded here: download openSMILE book. Installation instructions are also provided in the book. For the impatient: look for a suitable SMILExtract binary in the bin/ subdirectory of the release package and run it, run the script buildStandalone.sh to compile from source on Linux/Unix, or compile the Visual Studio solutions in ide/vs05 on Windows using Visual Studio 2005 or 2008. ... Then read then openSMILE book...

[ top ]

[ top ]

[ top ]

Acknowledgment: openSMILE's development has received funding from the European Community’s Seventh Framework Programme (FP7/2007-2013) under grant agreement No. 211486 (SEMAINE).