In this project we have developed a digital audio content identification system that enables on-line monitoring of multiple radio/TV channels. The proposed system consists of two main modules: “Digital audio watermarking” module and “audio fingerprinting” module. In order to obtain high identification accuracy, spread spectrum techniques will be used in the design of the modules.
The designed watermark (WM) encoder is a nonlinear data adaptive system that minimizes false alarm ratio by adaptively controlling the Watermark-to-Signal Ratio. Furthermore the conventional correlator decoder is modified in such a way that integrating synchronization and WM extraction into one processing step resulting in an on-line decoding scheme suitable to audio broadcast monitoring. Unlike the existing systems, a classifier-based WM decoder that models audio watermark decoding as a three class classification problem is also introduced. This allows not only extraction of embedded watermark bits but also discrimination of unwatermarked audio clips.