Robust Acoustic Event Classification using Fusion Fisher Vector features

Simple item page
dc.contributor.authorMulimani, M.
dc.contributor.authorKoolagudi, S.G.
dc.date.accessioned2026-02-05T09:29:23Z
dc.date.issued2019
dc.description.abstractIn this paper, a novel Fusion Fisher Vector (FFV) features are proposed for Acoustic Event Classification (AEC) in the meeting room environments. The monochrome images of a pseudo-color spectrogram of an acoustic event are represented as Fisher vectors. First, irrelevant feature dimensions of each Fisher vector are discarded using Principal Component Analysis (PCA) and then, resulting Fisher vectors are fused to get FFV features. Performance of the FFV features is evaluated on acoustic events of UPC-TALP dataset in clean and different noisy conditions. Results show that proposed FFV features are robust to noise and achieve overall 94.32% recognition accuracy in clean and different noisy conditions. © 2019 Elsevier Ltd
dc.identifier.citationApplied Acoustics, 2019, 155, , pp. 130-138
dc.identifier.issn0003682X
dc.identifier.urihttps://doi.org/10.1016/j.apacoust.2019.05.020
dc.identifier.urihttps://idr.nitk.ac.in/handle/123456789/24276
dc.publisherElsevier Ltd
dc.subjectClassification (of information)
dc.subjectSpectrographs
dc.subjectVectors
dc.subjectAcoustic event classification
dc.subjectFeature dimensions
dc.subjectFisher vectors
dc.subjectMonochrome images
dc.subjectNoisy conditions
dc.subjectRecognition accuracy
dc.subjectRoom environment
dc.subjectSpectrograms
dc.subjectPrincipal component analysis
dc.titleRobust Acoustic Event Classification using Fusion Fisher Vector features

Files

Collections

Journal Articles