BeamformIt acoustic beamformer

BeamformIt

(The fast and robust acoustic beamformer)

Introduction

BeamformIt is an acoustic beamforming tool that accepts a variable amount of input channels and computes an output via a filter&sum beamforming technique.

BeamformIt was originally implemented by Xavier Anguera at ICSI for participation to the NIST RT05s Meetings evaluation to deal with the different number of microphone channels available in a meeting room. BeamformIt was then rewritten and improved for the RT06s evaluation and finally readjusted and documented for public release.

BeamformIt was initially focused towards processing the data used in the RT evaluations but it can now process all sorts of data. As of version 3.5 an effort has been made to eliminate almost all external library dependencies and a script has been created for "casual" beamforming users to have an easy-to-use tool for their acoustic beamforming needs.

If you use the software for research I would very much appreciate if you could cite my work, you can use any of the following citations:

"Acoustic beamforming for speaker diarization of meetings", Xavier Anguera, Chuck Wooters and Javier Hernando, IEEE Transactions on Audio, Speech and Language Processing, September 2007, volume 15, number 7, pp.2011-2023.
"Robust Speaker Diarization for Meetings", Xavier Anguera, PhD Thesis, UPC Barcelona, 2006.

Download

BeamformIt-1.1.tar.gz

BeamformIt-2.0.tar.gz

BeamformIt-2.1.tar
(Includes a few bugfixes found in 2.0 since it was released.)

BeamformIt-3.3.tar.gz
(This version is still under development, some people have experienced problems in some files by using it)

BeamformIt-3.4.tar.gz
Stable version of BeamformIt version 3. It is a MUCH cleaner implementation in C++ of the classical BeamformIt.

BeamformIt-3.41.tar.gz
Some minor bugfixes and requested enhancements.

BeamformIt-3.5.tgz (released June 9th, 2014)
This version includes some major rewrites and parameterers change to make BeamformIt accessible for the casual user, and to make it less dependent on external libraries (we eliminated dependency with BOOST, libSamplerate and FFTW). As a result, speech researchers currently using previous versions should take care to read the documentation and set parameters correctly so that results are, at least, the same as in previous versions. The most important parameters for speech researchers are "delays_margin" and "skew_margin"/"do_compute_skew". The skew computation should only bother you if you are processing ICSI meetings.

BeamformIt-3.51.tgz (released July 7th, 2014)
This contains just a few bugfixes found in 3.5. This version is being used inside the AMI recipee for Kaldi. Thanks to Pawel Swietojanski for helping in the debugging and for implementing the AMI recipe for Kaldi, using BeamformIt.

Github repository (starting November 2015)
As of November 2015 BeamformIt will continue to grop inside Girhub. This will allow for constant improvements to be incorporated into the code. Feel free to fork the project and contribute to it!

Xavier Anguera (xanguera __--at--__ gmail.com), 2014