Published Paper Details:

In the digital age, the task of detecting music plagiarism has become increasingly critical to preserving the integrity of creative works. Music plagiarism detection involves the identification of similarities between musical pieces that may indicate unauthorized copying or infringement. A key element of this challenge is the accurate extraction and comparison of audio features from different tracks. In this paper, we present a novel approach that employs Python's librosa library to extract essential audio features and utilizes Euclidean distance to quantify the similarity between these features. To further refine the accuracy of plagiarism detection, we have integrated the K-Nearest Neighbors (KNN) machine learning algorithm, which classifies the audio samples based on their extracted features. The culmination of our approach is a detailed plagiarism report generated using the reportlab library, which provides comprehensive insights into the similarities between analyzed tracks. This method offers a systematic and robust solution for identifying potential cases of music plagiarism, contributing to the protection of intellectual property in the music industry.