Classification of Environmental Background Noise Sources Using Hilbert-Huang Transform

Abstract

 Abstract-Classification of common environmental background noise sources like train, airport, car and exhibition hall mixed with speech signals comprise of different utterances of various speakers required in many applications especially for forensic purposes. The acoustic features based on the Fourier and wavelet transformations are frequently used for environmental noise classification purpose. In the methodology presented, the noisy speech signal under test is initially decomposed into overlapped frames. In order to convert the latter into a set of bandlimited functions known as Intrinsic Mode Functions (IMFs), we use Empirical Mode Decomposition (EMD) method through Hilbert-Huang Transform (HHT). In this method the spectral and temporal features are extracted from the IMFs of different noisy speech signals and thereafter classification of different noise sources has been done using k-Nearest Neighbor (k-NN) classifier as a simpler way. Computed individual feature provides success rate of discrimination which varies from 77% to 85%. The combined feature vector enhances the success rate of classification as exhibited in the results. The technique presented reduces the dimensions of feature vector and proves the effectiveness of individual feature extracted from IMFs for the same.Index Terms-Hilbert-huang transform, intrinsic mode function, empirical mode decomposition, k-nearest neighbor classifier

Empirical Mode Decomposition for adaptive AM-FM analysis of Speech: A Review

“…(i) Speech Analysis -Enhancement/Denoising ( Flandrin et al, 20 04a;Rilling et al, 20 05;Boudraa et al, 20 06;Kopsinis and McLaughlin, 2009;Hasan and Hasan, 2009;Tsolis and Xenos, 2011;Chatlani and Soraghan, 2012;Hadhami and Bouzid, 2013 ), Pitch Tracking ( Yang et al, 2005;Huang and Pan, 2006;2010a ), Formant Tracking ( Huang and Chen, 2006;Bouzid and Ellouze, 2007 ), Pathological Voice Analysis ( Schlotthauer et al, 2010b;Kaleem et al, 2013;Mijovic et al, 2010 ), etc. (ii) Feature Extraction -Noise and audio Classification ( Jhanwar et al, 2013;Khonglah et al, 2015 ) , Emotion Classification ( Li and Li, 2011;He et al, 2011 ), Speaker Recognition ( Hasan and Hansen, 2011;Wu and Tsai, 2011 ), Voiced/Unvoiced speech classification ( Molla et al, 2008;Lu et al, 2009;Islam Molla et al, 2013;Sharma and Prasanna, 2015 ) etc.…”