Skip to main content

Learning Compact Structural Representations For Audio Events Using Regressor Banks

Phan, Huy, Maass, Marco, Hertel, Lars, Mazur, Radoslaw, McLoughlin, Ian Vince, Merins, Alfred (2016) Learning Compact Structural Representations For Audio Events Using Regressor Banks. In: 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing Proceedings. . IEEE ISBN 978-1-4799-9988-0. (doi:10.1109/ICASSP.2016.7471667) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided) (KAR id:55054)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided. (Contact us about this Publication)
Official URL
https://doi.org/10.1109/ICASSP.2016.7471667

Abstract

We introduce a new learned descriptor for audio signals which is

produced by evaluating a set of regressors on the input signal. The

forests framework. Given an input signal, each regressor estimates

fidence scores output by a regressor are then used to quantify how

category. Our proposed descriptor has two advantages. First, it

number of event classes. Second, we show that even simple linear

on audio event classification task than not only the nonlinear

baselines but also the state-of-the-art results.

Item Type: Conference or workshop item (Proceeding)
DOI/Identification number: 10.1109/ICASSP.2016.7471667
Uncontrolled keywords: feature learning; audio event; recognition; structural encoding
Subjects: T Technology
Divisions: Faculties > Sciences > School of Computing
Depositing User: Ian McLoughlin
Date Deposited: 19 Apr 2016 10:52 UTC
Last Modified: 29 May 2019 17:14 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/55054 (The current URI for this page, for reference purposes)
Phan, Huy: https://orcid.org/0000-0003-4096-785X
McLoughlin, Ian Vince: https://orcid.org/0000-0001-7111-2008
  • Depositors only (login required):