Enhancement of Urban Sound Classification Using Various Feature Extraction Techniques
Afshankaleem1, I. Santi Prabha2
1Afshankaleem, Sr. Assistant Professor, Department of ECE, MJCET, Hyderabad (Telangana), India.
2Dr. I. Santi Prabha, Professor, Department of ECE, JNTUCE, JNTUK, Kakinada (Andhra Pradesh), India.
Manuscript received on 25 April 2019 | Revised Manuscript received on 03 May 2019 | Manuscript Published on 08 May 2019 | PP: 507-514 | Volume-7 Issue-5S3 February 2019 | Retrieval Number: E11900275S19/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this paper we describe few methods of extracting features from sound data, one commonly used feature extraction technique in speech recognition is isolating the Mel Frequencies Cepstral Coefficients (MFCC). The accuracy of speech recognition systems, to a large extent, depends on the feature sets used for representing the recorded speech data. It has been a continuous process to derive better feature sets for more accurate speech recognition using ASR (Automatic Speech Recognition) systems. Many feature sets and their different combinations have been tried to achieve better accuracy but a feature set providing completely accurate results has not yet been formulated. These large feature sets consume significant amount of memory, together with computing and power requirements and they do not always contribute to improve the recognition rate. There are few commonly used features extraction methods, such as Mel-scaled spectrogram, Chroma gram, spectral-contrast, and the tonal centroid features We go on to detail the effectiveness of different models on each method, including tests of Random Forests, Naïve Bayes,J48, SVM, Machines architectures.
Keywords: Mel Banks Cepstral Coefficients (MFCC), Sound Classification, Feature Extraction.
Scope of the Article: Classification