Improved wireless acoustic sensor network for analysing audio properties

In this study, a Wireless Acoustic Sensor Network (WASN) technique has been designed for evaluating various features of audio signals and assessing different audio qualities in a distributed and effective manner. The method is essentially divided into two crucial parts- feature extraction and categorizing the extracted features with the help of the Support Vector Machine (SVM). The SVM algorithm divides the audio features into multiple standard categories with executing other steps of the proposed method’s implementation- preprocessing, digitization, voice centering, organizing the audio signal and transforming the analogue signal into digital data format for further processing. The performance analysis is supported with comparisons with the existing methods. The suggested method is a full and cost effective solution for audio analysis in a WASN, and it is highly beneficial for different speech recognition, voice identification, along with detecting acoustic based criminal activities. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management.