[mythtv] New Method for Commercial Detection.

[Robert Dunn]

Hi,

I am an embedded developer for the most part (writing code for the Texas 
Instruments range of Digital Signal Processors) recently I have devoted 
a lot of my spare time playing with audio fingerprinting on these DSPs 
with the ultimate goal of creating a PVR Box with in built commercial 
detection using a modified version of the audio fingerprinting technique 
discussed here http://ismir2002.ismir.net/proceedings/02-FP04-2.pdf

I have had a lot of success with this project so far, most of which is a 
proof of concept that the audio fingerprinting technique could be used 
for commercial detection and implementing the algorithm on a somewhat 
resource constrained device. The next step of my project is to fine tune 
the detection and searching algorithms and create working PC software 
before I move over to a fully embedded solution (and in the process 
create software which people who dont have the money/expertise to build 
the DSP based system can use instead).

The advantages of a system like this is that it does not rely on any 
'coincidental' difference between the commercials and the programming 
such as the volume, as technically it could be taught to eliminate any 
piece of video/audio, but of course relies on having an up-to-date set 
of commercial keys, but I have in my work touched on some techniques in 
keeping the keys up to date automatically.

MythTV seems like the perfect platform for me to build upon, both saving 
me time, and giving something back to the open source community. Whilst 
I am not a student, I noticed you are looking for people to develop the 
commercial detection aspect of MythTV for the Google Summer of Code.

Is this something you guys would be interested in having me work on? 
Please get back to me with any thoughts.

Thanks in advance,

Rob.