Detecting Audio / Video Asynchrony

Asynchrony between the audio and video track in streaming video can cause user frustration with the service but often goes unreported. Providers of on-demand internet streaming media such as Netflix reach millions of users and thus are concerned with supplying correctly aligned audio/video content. Our project will attempt to detect A/V misalignment in standard (nonstreaming) movie clips. We expect that if certain time-dependent video and audio features are correlated, we should be able to predict the misalignment of a video and audio track by comparing the progression of these audio and video features over a segment of the movie clip.