Multimedia Database Management System | UW, Bothell | Spring 2015 |
A stand-alone application that can be used to,
- Classify a set of audio files as speech/music, from a given a user-specified set by using Machine learning and Audio feature analysis.
- Reconfigured OTS tool - jAudio , to extract specific audio features and integrated with Weka (feedback extracted audio features as i/p) for predictive (Decision Tree Algorithm) modelling in order to return the type of audio.
Overall precision ~ 70%.