(Sorry for cross-posting, on [Opencast] it was suggested that we should
post here ...)
Hi all,
We are building a free automatic audio post production web service
called *Auphonic*, which I think you might be interested in:
Here is our website:
http://auphonic.com
And a two-minute video:
https://www.youtube.com/watch?v=Y6uXP-MGt8I
Audio post production of lecture recordings is an area that we are
particularly interested in, and where we have acquired experience
through an ongoing collaboration with the Graz University of Technology.
Our service has also attracted many users from the German-speaking
podcasting scene since it has gone public this spring.
To us it seems that the workflows supported by Matterhorn and Auphonic
complement each other very well. Auphonic could provide algorithms for
automated audio post production within the Matterhorn environment, such
as noise reduction or equalizing loudness differences between the
lecturer (who is usually equipped with a microphone) and the audience
(who often isn't).
Auphonic is built almost exclusively from Open Source software
components (e.g., NumPy, SciPy, Yaafe, ffmpeg, libsndfile, Django), and
we aim at contributing our own developments back to the Open Source
community.
We maintain a very close dialogue with our users and constantly
implement new feature requests and ideas that they contribute. We would
welcome a collaboration with the Matterhorn project to learn more about
our users' needs in this area.
If you are interested in establishing a dialogue on how Matterhorn and
Auphonic could complement each other, I'd be more than happy to answer
any questions that you might have. You also might want to check out our
REST API:
https://auphonic.com/developers
Kind regards,
Florian + Georg
P.S.: Here is a short list of features that we support:
- Automatic audio classification (music and speech detection, noise
profiling, etc.) by server-based machine-learning algorithms
- Adaptive leveling to equalize volumes for different regions:
https://auphonic.com/blog/2012/03/27/auphonic-audio-post-production-now-open-public-users/#algorithms
- Loudness normalization according to new, consistent standards:
https://auphonic.com/blog/2012/08/02/loudness-measurement-and-normalization-ebu-r128-calm-act/
- Automatic filtering, compression, and limiting where necessary
- Automatic noise reduction, also for changing noise profiles:
https://auphonic.com/blog/2012/05/11/experimental-noise-reduction-and-algorithm-chooser/
- Encoding to various file formats (MP3, Opus, Vorbis, AAC, FLAC, etc.)
- Video support for input and output (all popular formats)
- Metadata and chapter marks support for all file formats
- Automatic content deployment via (S)FTP, Soundcloud, YouTube,
Dropbox
--
auphonic - automatic audio post production
http://auphonic.com
audio development, machine learning, open source and more
_______________________________________________
Matterhorn mailing list
[email protected]
http://lists.opencastproject.org/mailman/listinfo/matterhorn
To unsubscribe please email
[email protected]
_______________________________________________
