Abstract:
A method is presented for content-based audio classication and retrieval. It is based on a new pattern classication method called the nearest Feature Line (NFL). In the NFL, information provided by multiple prototypes per class is explored. This contrasts to the nearest neighbor (NN) classication in which the query is compared to each prototype individually. Regarding audio representation, perceptual and cepstral features and their combinations are considered. Extensive experiments are performed to compare various classication methods and feature sets. The results show that the NFL-based method produces consistently better results than the NN-based and other methods. A system resulting from this work has achieved the error rate of 9.78%, as compared to that of 18.34 % of a compelling existing system, as tested on a common audio database.
Citations
|
1712
|
Introduction to Statistical Pattern Recognition
– Fukunaga
- 1990
|
|
929
|
Biing-Hwang Juang, Fundamentals of Speech Recognition
– Rabiner
- 1993
|
|
759
|
Visual Learning and Recognition of 3-D Objects from Appearance
– Murase, Nayar
- 1995
|
|
98
|
Content-based retrieval of music and audio
– Foote
- 1997
|
|
64
|
Audio feature extraction and analysis for scene segmentation and classification
– Liu, Wang, et al.
- 1998
|
|
52
|
Automatic audio content analysis
– Pfeiffer, Fischer, et al.
- 1996
|
|
43
|
Automatic indexing of a sound database using self-organizing neural nets
– Feiten, Günzel
- 1994
|
|
40
|
Face recognition using the nearest feature line method
– Li, Lu
- 1999
|
|
14
|
Organizing sounds with neural nets
– Feiten, Ungvary
- 1991
|
|
8
|
Toward an intelligent editor of digital audio: Signal processing methods
– Foster, Schloss, et al.
- 1982
|
|
6
|
Face Recognition Based on Nearest Linear Combinations
– Li
- 1998
|
|
5
|
Content-based classi search and retrieval of audio
– Wold, Blum, et al.
- 1996
|
|
2
|
An overview of audio information retrieval". ACM-Springer Multimedia Systems
– Foote
- 1998
|
|
2
|
Audio and Video Retrieval Based on Audio Content
– Rice
- 1998
|
|
1
|
Modelling Auditory Processing and Organisation, Cambrige
– Cook
- 1993
|
|
