Abstract
A formula to compute the similarity between two audio feature vectors is proposed, which can map arbitrary pair of vectors with equivalent dimension to [0, 1). To fulfill the task of audio segmentation, a self-similarity matrix is computed to reveal the inner structure of an audio clip to be segmented. As the final result must be consistent with the subjective evaluation and be adaptive to some special applications, a set of weights is adopted, which can be modified through relevance feedback techniques. Experiments show that satisfactory result can be achieved via the algorithm proposed in this paper.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Woodland P C, Hain T, Johnson S,et al. Experiments in Broadcast News Transcription.Proc IEEE International Conference on Acoustics, Speech, and Signal Processing, 1998,2:909–912.
Sankar A, Weng F, Rivlin Z,et al. The Development of SRI’s 1997 Broadcast News Transcription System.Proc DARPA Broadcast News Transcription and Understanding Workshop, 1998,1:91–96.
Siegler M A, Jain U, Raj B,et al. Automatic Segmentation, Classification and Clustering of Broadcast News Audio.Proc DARPA Speech Recognition Workshop, 1997,1:97–99.
Tzanetakis G, Cook P. Multifeature Audio Segmentation for Browsing and Annotation.Proc IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 1999,1:103–106.
Nitanda N, Haseyama M, Kitajima H. Audio-Cut Detection and Audio-Segment Classification Using Fuzzy C-Means Clustering.Proc IEEE International Conference on Acoustics, Speech, and Signal Processing 2004,4:325–328.
Tzanetakis G, Cook P. Marsyas: A Framework for Audio Analysis.Organized Sound, 2000,10(5):293–302.
Linäker F, Niklasson L. Time Series Segmentation Using an Adaptive Resource Allocating Vector Quantization Network Based on Change Detection.International Joint Conference on Neural Networks, 2000,6:323–328.
Church K, Helfman J. Dotplot: A Program for Exploring Self-Similarity in Millions of Lines of Text and Code.J American Statistical Assoc, 1993,2(2):153–174.
Eckmann J P, Kamphorst S O, Ruelle D. Recurrence Plots of Dynamical Systems.Europhys Lett, 1987,4(9):973–977.
Rui Y, Huang T S, Orgeta M,et al. Relevance Feedback: A Power Tool for Interactive Content-Based Image Retrieval.J IEEE Trans on Circuits and Video Technology, 1998.8(5):644–655.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Foundation item: Supported by the National Natural Science Foundation of China (10371033)
Biography: CHEN Gang (1970-), male, Ph. D. candidate, research direction: audio analysis and pattern recognition.
Rights and permissions
About this article
Cite this article
Gang, C., Hui, T. & Xin-meng, C. Audio segmentation via the similarity measure of audio feature vectors. Wuhan Univ. J. Nat. Sci. 10, 833–837 (2005). https://doi.org/10.1007/BF02832422
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02832422
Key words
- audio segmentation
- abrupt change detection
- overall error
- similarity measure
- self-similarity matrix
- relevance feedback