An Efficient Approach for Segmentation, Feature Extraction and Classification of Audio Signals

Abstract

Due to the presence of non-stationarities and discontinuities in the audio signal, segmentation and classification of audio signal is a really challenging task. Automatic music classification and annotation is still considered as a challenging task due to the difficulty of extracting and selecting the optimal audio features. Hence, this paper proposes an efficient approach for segmentation, feature extraction and classification of audio signals. Enhanced Mel Frequency Cepstral Coefficient (EMFCC)-Enhanced Power Normalized Cepstral Coefficients (EPNCC) based feature extraction is applied for the extraction of features from the audio signal. Then, multi-level classification is done to classify the audio signal as a musical or non-musical signal. The proposed approach achieves better performance in terms of precision, Normalized Mutual Information (NMI), F-score and entropy. The PNN classifier shows high False Rejection Rate (FRR), False Acceptance Rate (FAR), Genuine Acceptance rate (GAR), sensitivity, specificity and accuracy with respect to the number of classes.

Content‐Based Audio Classification and Retrieving Using Modified Bacterial Foraging Optimization Algorithm

“…Te identifcation of bird songs may also be accomplished with the help of multi-modal deep CNN by using audio samples and metadata as inputs. Utilizing quadratic time-frequency distributions [13], an audio surveillance system has been developed to prevent automobile collisions and tyre sliding in hazardous situations. Te efective music indexing framework (EMIF) has been created [14] with the goals of increasing the efciency of queries and facilitating the retrieval of scalable and accurate music.…”

Classification of Ontological Violence Content Detection through Audio Features and Supervised Learning

“…Though this energy entropy features can detect the violent content more successfully, some non-violent sounds like thunders are also detected as violence. Further, one more method is developed in [5] to segment and classify the audio signals based on the signals entropy. Next, the authors of [6] developed a new method based on Machine Learning and signal processing techniques to identify the vocal and non-vocal regions of the songs.…”