Opensmile

TLDR

We introduce openSMILE, a C++ feature‑extraction toolkit that unites algorithms from speech processing and music information retrieval. openSMILE supports a wide array of low‑level audio descriptors (CHROMA, CENS, MFCC, PLP, LPC, LSF, F0, formants), applies delta regression and statistical functionals, is dependency‑free, and guarantees future compatibility through unit tests. The toolkit is fast, cross‑platform (Unix/Windows), modular with plug‑in extensibility, supports online incremental, offline, and batch processing, and is freely downloadable from its website.

Abstract

We introduce the openSMILE feature extraction toolkit, which unites feature extraction algorithms from the speech processing and the Music Information Retrieval communities. Audio low-level descriptors such as CHROMA and CENS features, loudness, Mel-frequency cepstral coefficients, perceptual linear predictive cepstral coefficients, linear predictive coefficients, line spectral frequencies, fundamental frequency, and formant frequencies are supported. Delta regression and various statistical functionals can be applied to the low-level descriptors. openSMILE is implemented in C++ with no third-party dependencies for the core functionality. It is fast, runs on Unix and Windows platforms, and has a modular, component based architecture which makes extensions via plug-ins easy. It supports on-line incremental processing for all implemented features as well as off-line and batch processing. Numeric compatibility with future versions is ensured by means of unit tests. openSMILE can be downloaded from http://opensmile.sourceforge.net/.