Environmental Sound Recognition (ESR) with Python

Yusuf Saraçlıoglu, Bilal Saoud, Ibraheem Abdullah Mohammed Shayea, Yong Pil Geum, Leila Rzayeva

2025

Closed access Metadata (CSL-JSON)
DOI 10.1109/snpd65828.2025.11254371
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Environmental Sound Recognition (ESR) is an essential task in audio analysis, involving the identification and classification of sounds from various environmental contexts. This study employs machine learning techniques, specifically Support Vector Machines (SVM), to classify sounds from the ESC-10 dataset. We extracted key audio features, including Mel Frequency Cepstral Coefficients (MFCCs), Chroma, and Mel spectrograms using the Librosa library. Our approach highlights the potential of SVM in ESR tasks, with promising applications in urban monitoring, smart cities, and automated surveillance systems.