We describe algorithms for automated quality assurance on content of audio files in context of preservation actions and access. The algorithms use cross correlation to compare the sound waves. They are used to do overlap analysis in an access scenario, where preserved radio broadcasts are used in research and annotated. They have been applied in a migration scenario, where radio broadcasts are to be migrated for long term preservation.
Proceedings of the 9th International Conference on Preservation of Digital Objects, Ipres, 2012, p. 144-149