AudioSeg AudioSeg is a toolkit dedicated to audio segmentation and classification of audio streams.
Download

AudioSeg Ranking & Summary

AudioSeg Tags

audio audio segmentation stream classifier silence detector segmentation silence

AudioSeg Description

AudioSeg is a toolkit dedicated to audio segmentation and classification of audio streams. AudioSeg is a toolkit dedicated to audio segmentation and classification of audio streams. The toolkit implements standard reference algorithms such as energy-based silence detection, BIC segmentation and clustering as well as GMM/HMM classification.Here are some key features of "AudioSeg":· silence / audio activity detection· blind segmentation with the Bayesian information criterion· segment clustering· segment classification with Gaussian mixture models· joint segmentation and classification using hidden Markov modelsRequirements:· SPro >= 4.0INSTALLATION:Installation follows the standard GNU installation procedure. From thepackage top level directory, the commands >> ./configure >> makewill build the library and the runtimes, located in the srcdirectory. Since AudioSeg rely on the SPro 4.0, the location of SPromust be specified with --with-spro SPro location (requires SPro 4.0 or greater)If SPro was installed with the SPHERE package support, this must alsobe specified with --with-sphere SPHERE file format support (requires SPHERE 2.6)See configure --help for more details on the configuration script options. Installing the library and the runtimes can be done by >> make installThe installation path is specified by the configuration script (try./configure --help for details) and defaults to /usr/local.What's New in This Release:· switched from SPro 3.3.1 to SPro 4.0· unified option switches accross tools· unique header and library

AudioSeg Related Software