Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

LEARNING COMPACT STRUCTURAL REPRESENTATIONS FOR AUDIO EVENTS USING REGRESSOR BANKS

Bank of regressors
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.

up
0 users have voted:

Paper Details

Authors:
Huy Phan, Marco Maass, Lars Hertel, Radoslaw Mazur, Ian McLoughlin, Alfred Mertins
Submitted On:
16 March 2016 - 9:03am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Huy Phan
Document Year:
2016
Cite

Document Files

1838_poster.pdf

(267 downloads)

Subscribe

[1] Huy Phan, Marco Maass, Lars Hertel, Radoslaw Mazur, Ian McLoughlin, Alfred Mertins, "LEARNING COMPACT STRUCTURAL REPRESENTATIONS FOR AUDIO EVENTS USING REGRESSOR BANKS", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/712. Accessed: Apr. 26, 2018.
@article{712-16,
url = {http://sigport.org/712},
author = {Huy Phan; Marco Maass; Lars Hertel; Radoslaw Mazur; Ian McLoughlin; Alfred Mertins },
publisher = {IEEE SigPort},
title = {LEARNING COMPACT STRUCTURAL REPRESENTATIONS FOR AUDIO EVENTS USING REGRESSOR BANKS},
year = {2016} }
TY - EJOUR
T1 - LEARNING COMPACT STRUCTURAL REPRESENTATIONS FOR AUDIO EVENTS USING REGRESSOR BANKS
AU - Huy Phan; Marco Maass; Lars Hertel; Radoslaw Mazur; Ian McLoughlin; Alfred Mertins
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/712
ER -
Huy Phan, Marco Maass, Lars Hertel, Radoslaw Mazur, Ian McLoughlin, Alfred Mertins. (2016). LEARNING COMPACT STRUCTURAL REPRESENTATIONS FOR AUDIO EVENTS USING REGRESSOR BANKS. IEEE SigPort. http://sigport.org/712
Huy Phan, Marco Maass, Lars Hertel, Radoslaw Mazur, Ian McLoughlin, Alfred Mertins, 2016. LEARNING COMPACT STRUCTURAL REPRESENTATIONS FOR AUDIO EVENTS USING REGRESSOR BANKS. Available at: http://sigport.org/712.
Huy Phan, Marco Maass, Lars Hertel, Radoslaw Mazur, Ian McLoughlin, Alfred Mertins. (2016). "LEARNING COMPACT STRUCTURAL REPRESENTATIONS FOR AUDIO EVENTS USING REGRESSOR BANKS." Web.
1. Huy Phan, Marco Maass, Lars Hertel, Radoslaw Mazur, Ian McLoughlin, Alfred Mertins. LEARNING COMPACT STRUCTURAL REPRESENTATIONS FOR AUDIO EVENTS USING REGRESSOR BANKS [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/712