Please use this identifier to cite or link to this item:
Title: Investigation on the Effect of the Input Features in the Noise Level Classification of Noisy Speech
Authors: Dash, T K
Solanki, S S
Keywords: Noise Level Estimation;PCA;Neighbourhood Component Feature Selection;Speech Enhancement;Noise Level classification
Issue Date: Dec-2019
Publisher: NISCAIR-CSIR, India
Abstract: Noise Level Estimation plays a crucial role in Speech Enhancement (SE) Algorithms. Recently, few noise estimation (NE) algorithms are developed for SE using the minimal-tracking method, but there is little research done in the noise level classification (NLC). Therefore, there is a need to identify appropriate audio features that are required for the NLC. In this paper, this problem has been addressed and seventeen audio features of the noisy speech are examined for NLC using four different types of standard and efficient classifiers such as K-Nearest Neighbor (KNN), Naive Bayes (NB), Support Vector Machine (SVM), Decision Tree (DT) classifiers. The features are first optimized to achieve the best classification performance using the Principal Component Analysis (PCA) and the Neighbourhood Component Feature Selection (NCFS) method. Finally, a comparative performance analysis is carried out by taking six different categories of real-life noisy speech signals from the standard speech database and then the best set of features are reported and the best performing classifier for the NLC is identified.
Page(s): 868-872
ISSN: 0975-1084 (Online); 0022-4456 (Print)
Appears in Collections:JSIR Vol.78(12) [December 2019]

Files in This Item:
File Description SizeFormat 
JSIR 78(12) 868-872.pdf515.94 kBAdobe PDFView/Open

Items in NOPR are protected by copyright, with all rights reserved, unless otherwise indicated.