Feature Selection: Evaluation, Application, and Small Sample Performance
IEEE Transactions on Pattern Analysis and Machine Intelligence
Adaptive floating search methods in feature selection
Pattern Recognition Letters - Special issue on pattern recognition in practice VI
Machine Learning
Prediction-driven computational auditory scene analysis
Prediction-driven computational auditory scene analysis
Highlight sound effects detection in audio stream
ICME '03 Proceedings of the 2003 International Conference on Multimedia and Expo - Volume 3 (ICME '03) - Volume 03
Long-time span acoustic activity analysis from far-field sensors in smart homes
ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
A study on speaker adaptation of the parameters of continuousdensity hidden Markov models
IEEE Transactions on Signal Processing
IEEE Transactions on Information Theory
Effective browsing of long audio recordings
Proceedings of the 2nd ACM international workshop on Interactive multimedia on mobile and portable devices
A context aware sound classifier applied to prawn feed monitoring and energy disaggregation
Knowledge-Based Systems
Multimedia Tools and Applications
Hi-index | 0.10 |
Acoustic Event Detection (AED) aims to identify both timestamps and types of events in an audio stream. This becomes very challenging when going beyond restricted highlight events and well controlled recordings. We propose extracting discriminative features for AED using a boosting approach, which outperform classical speech perceptual features, such as Mel-frequency Cepstral Coefficients and log frequency filterbank parameters. We propose leveraging statistical models better fitting the task. First, a tandem connectionist-HMM approach combines the sequence modeling capabilities of the HMM with the high-accuracy context-dependent discriminative capabilities of an artificial neural network trained using the minimum cross entropy criterion. Second, an SVM-GMM-supervector approach uses noise-adaptive kernels better approximating the KL divergence between feature distributions in different audio segments. Experiments on the CLEAR 2007 AED Evaluation set-up demonstrate that the presented features and models lead to over 45% relative performance improvement, and also outperform the best system in the CLEAR AED Evaluation, on detection of twelve general acoustic events in a real seminar environment.