Paper Info
Title
A Discriminative and Compact Audio Representation for Event Detection.
Abstract
This paper presents a novel two-phase method for audio representation: Discriminative and Compact Audio Representation (DCAR). In the first phase, each audio track is modeled using a Gaussian mixture model (GMM) that includes several components to capture the variability within that track. The second phase takes into account both global structure and local structure. In this phase, the components are rendered more discriminative and compact by formulating an optimization problem on Grassmannian manifolds, which we found represents the structure of audio effectively. Experimental results on the YLI-MED dataset show that the proposed DCAR representation consistently outperforms state-of-the-art audio representations: i-vector, mv-vector, and GMM.
Year
DOI
Venue
2016
10.1145/2964284.2970377
ACM Multimedia
Keywords
Field
DocType
Event Detection,Audio Data,Discriminative and Compact Representation
Global structure,Pattern recognition,Computer science,Local structure,Speech recognition,Grassmannian,Artificial intelligence,Discriminative model,Optimization problem,Mixture model,Manifold
Conference
Citations 
PageRank 
References 
2
0.38
8
Authors
7
Name
Order
Citations
PageRank
Liping Jing155047.13
Bo Liu252184.67
Jae-Young Choi3783110.19
Adam Janin425034.11
Julia Bernd5194.98
Michael W. Mahoney63297218.10
Gerald Friedland7112796.23