Learning compact structural representations for audio events using regressor banks

H. Phan, M. Maass, L. Hertel, R. Mazur, Ian McLoughlin, A. Mertins


We introduce a new learned descriptor for audio signals which is efficient for event representation. The entries of the descriptor are produced by evaluating a set of regressors on the input signal. The regressors are class-specific and trained using the random regression forests framework. Given an input signal, each regressor estimates the onset and offset positions of the target event. The estimation confidence scores output by a regressor are then used to quantify how the target event aligns with the temporal structure of the corresponding category. Our proposed descriptor has two advantages. First, it is compact, i.e. the dimensionality of the descriptor is equal to the number of event classes. Second, we show that even simple linear classification models, trained on our descriptor, yield better accuracies on audio event classification task than not only the nonlinear baselines but also the state-of-the-art results.
Original languageEnglish
Title of host publication2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Number of pages5
Publication date01.03.2016
Article number7471667
ISBN (Print)978-1-4799-9987-3
ISBN (Electronic)978-1-4799-9988-0
Publication statusPublished - 01.03.2016
Event41st IEEE International Conference on Acoustics, Speech and Signal Processing - Shanghai International Convention Center , Shanghai, China
Duration: 20.03.201625.03.2016
Conference number: 121667

Cite this