Robust Music Identification, Detection, and Analysis

In previous work, we presented a new approach to music identification based on finite-state transducers and Gaussian mixture models. Here, we expand this work and study the performance of our system in the presence of noise and distortions. We also evaluate a song detection method based on a universal background model in combination with a support vector machine classifier and provide some insight into why our transducer representation allows for accurate identification even when only a short song snippet is available.