Learning compact structural representations for audio events using regressor banks

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

Abstract

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.
OriginalspracheEnglisch
Titel2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Seitenumfang5
Band2016-May
Herausgeber (Verlag)IEEE
Erscheinungsdatum01.03.2016
Seiten211-215
Aufsatznummer7471667
ISBN (Print)978-1-4799-9987-3
ISBN (elektronisch)978-1-4799-9988-0
DOIs
PublikationsstatusVeröffentlicht - 01.03.2016
Veranstaltung41st IEEE International Conference on Acoustics, Speech and Signal Processing - Shanghai International Convention Center , Shanghai, China
Dauer: 20.03.201625.03.2016
Konferenznummer: 121667

Fingerprint

Untersuchen Sie die Forschungsthemen von „Learning compact structural representations for audio events using regressor banks“. Zusammen bilden sie einen einzigartigen Fingerprint.

Zitieren