This Wavesurfer plugin uses a power threshold to judge whether a frame is to be considered silent or not. It is intended for rough on-the-fly analyses, not for production use.
The code is available for download under a BSD-style open source license. The silence plug-in is a beta.
Description
A simple silence detector, working along the following lines:
- The plugin uses a power threshold to decide whether a sound frame is silent or not.
- The threshold can be given manually or be computed over a selected (presumably silent) area in a sound file
- The threshold can be computed with an automatic silence estimation over the whole file
- A minimum time of silence can be given - any silences shorter than that will be skipped.
- A maximum number of non-silent frames in the silent sequences can also be set, in order to allow for sound artefacts.
- The result can be exported as a label file in .lab format.
Future plans
- More sophisticated algorithms
- Export of silent or non-silent sections as audio files
- Other export formats (dataplot)
- Incremental (on-line) calculation
- Calibration based on standard deviations
- Auto-calibration based on static power level detection.
- On-line auto-calibration
- Add padding option to pad the non-silent bits after calculation
- Include configurable power calculation from the analysis plugin
Download
The code is beta status and publically available, but the documentation is lacking. It can be downloaded at the following location:
- Wavesurfer Silence plug-in (v. 0.2) (download and save in your Wavesurfer plugins directory)
- Wavesurfer Silence plugin (v. 0.2) configration example (download and save in your Wavesurfer configurations directory)
Version history
0.2
- Fixed bug that caused misalignment
- The threshold can be computed with an automatic silence estimation over the whole file
- The power calculation now uses the Wavesurfer analysis plugin's standard settings
0.1
- The plugin uses a power threshold to decide whether a sound frame is silent or not.
- The threshold can be given manually or be computed over a selected (presumably silent) area in a sound file
- A minimum time of silence can be given - any silences shorter than that will be skipped.
- A maximum number of non-silent frames in the silent sequences can also be set, in order to allow for sound artefacts.
- The result can be exported as a label file in .lab format.
Licence
The silence plugin is copyright © 2004 Jens Edlund and distributed under the following license:
The following terms apply to all files associated with the software unless explicitly disclaimed in individual files.
The author hereby grant permission to use, copy, modify, distribute, and license this software and its documentation for any purpose, provided that existing copyright notices are retained in all copies and that this notice is included verbatim in any distributions. No written agreement, license, or royalty fee is required for any of the authorized uses. Modifications to this software may be copyrighted by their authors and need not follow the licensing terms described here, provided that the new terms are clearly indicated on the first page of each file where they apply.
IN NO EVENT SHALL THE AUTHORS OR DISTRIBUTORS BE LIABLE TO ANY PARTY FOR DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OF THIS SOFTWARE, ITS DOCUMENTATION, OR ANY DERIVATIVES THEREOF, EVEN IF THE AUTHORS HAVE BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
THE AUTHORS AND DISTRIBUTORS SPECIFICALLY DISCLAIM ANY WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, AND NON-INFRINGEMENT. THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, AND THE AUTHORS AND DISTRIBUTORS HAVE NO OBLIGATION TO PROVIDE MAINTENANCE, SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS.
Copyright © 2002-2004 Jens Edlund, Gabriel Skantze and the members of the Center for Speech Technology