We propose a video event analysis framework based on object segmentation and tracking, combined with a Hidden Semi-Markov Model (HSMM) that uses state occupancy duration modeling....
We propose a new approach for singer melody extraction, based on blind source separation techniques. The short time Fourier transform (STFT) of the singer signal is modelled by a ...
We propose novel approaches for optimizing the detection performance in spoken language recognition. Two objective functions are designed to directly relate model parameters to tw...
This paper addresses the problem of Voice Active Detection (VAD) in noisy environments. We introduce Variational Bayes approach to EM for classification to replace the heuristic ...
An algorithm for extracting music fingerprints directly from an audio signal is proposed in this paper. The proposed music fingerprint aims to encapsulate various aspects of mus...