Paper Info
Title
An enhanced fuzzy c-means algorithm for audio segmentation and classification
Abstract
Automated audio segmentation and classification play important roles in multimedia content analysis. In this paper, we propose an enhanced approach, called the correlation intensive fuzzy c-means (CIFCM) algorithm, to audio segmentation and classification that is based on audio content analysis. While conventional methods work by considering the attributes of only the current frame or segment, the proposed CIFCM algorithm efficiently incorporates the influence of neighboring frames or segments in the audio stream. With this method, audio-cuts can be detected efficiently even when the signal contains audio effects such as fade-in, fade-out, and cross-fade. A number of audio features are analyzed in this paper to explore the differences between various types of audio data. The proposed CIFCM algorithm works by detecting the boundaries between different kinds of sounds and classifying them into clusters such as silence, speech, music, speech with music, and speech with noise. Our experimental results indicate that the proposed method outperforms the state-of-the-art FCM approach in terms of audio segmentation and classification.
Year
DOI
Venue
2013
10.1007/s11042-011-0921-z
Multimedia Tools Appl.
Keywords
Field
DocType
Audio segmentation and classification,Fuzzy c-means algorithm,Multimedia,Database retrieval
Audio content analysis,Speech coding,Computer science,Artificial intelligence,Computer vision,Pattern recognition,Audio segmentation,Audio mining,Database retrieval,Fuzzy logic,Algorithm,Speech recognition,Multimedia content analysis,Acoustic model
Journal
Volume
Issue
ISSN
63
2
1380-7501
Citations 
PageRank 
References 
4
0.39
16
Authors
2
Name
Order
Citations
PageRank
Mohammad A. Haque19910.07
Jong-Myon Kim29125.99