Noisy Node Detection in Wave File by using Iterative Silhouette Clustering and Vivaldi

Abstract

There are various approaches for the noise detection in the audio files. Human ear can detect the sound intensity change of 34 milliseconds. In this paper propose novel method for noisy node detection in the wave file. The wave file is divided in chunks depending on Vivaldi concept. Iterative k-means clusters are created. The silhouette noisy node is detected, by comparing silhouette nodes in all iteration for each chunk.