Real-time discrimination of broadcast speech/music
- 24 December 2002
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings
- Vol. 2, 993-996 vol. 2
- https://doi.org/10.1109/icassp.1996.543290
Abstract
We describe a technique which is successful at discriminating speech from music on broadcast FM radio. The computational simplicity of the approach could lend itself to wide application including the ability to automatically change channels when commercials appear. The algorithm provides the capability to robustly distinguish the two classes and runs easily in real time. Experimental results to date show performance approaching 98% correct classification.Keywords
This publication has 3 references indexed in Scilit:
- Detection of human speech in structured noisePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Spectral analysis and discrimination by zero-crossingsProceedings of the IEEE, 1986
- Automatic segmentation of speech into syllabic unitsThe Journal of the Acoustical Society of America, 1975