Name
Title | ||
|---|---|---|
Specific Selection of FFT Amplitudes from Audio Sports and News Broadcasting for Classification Purposes |
Abstract | ||
|---|---|---|
In this paper we investigate the problem of classification between sports and news broadcasting. We detect and classify files that consist of speech and music or background noise (news broadcasting), and speech and a noisy background (sports broadcasting). More specifically, this study investigates feature extraction and training and classification proce- dures. We compare the Average Magnitude Difference Function (AMDF) method, which we consider more robust to background noise, with a novel proposed method. This method uses several spectral audio features which may be considered as specific semantic information. We base the extrac- tion of these features on the theory of computational geometry using an Onion Algorithm (OA). We tested the classification procedure as well as the learning ability of the two methods using a Learning Vector Quantizer One (LVQ1) neural network. The results of the experiment showed that the OA method has a faster learning procedure, which we characterise as an accurate feature extraction method for several audio cases. |
Year | Venue | Keywords |
|---|---|---|
2007 | J. Graph Algorithms Appl. | neural network,feature extraction,learning vector quantization |
Field | DocType | Volume |
Broadcasting,Background noise,Pattern recognition,Computer science,Computational geometry,Speech recognition,Feature extraction,Fast Fourier transform,Artificial intelligence,Broadcasting of sports events,Quantization (signal processing),Artificial neural network | Journal | 11 |
Issue | Citations | PageRank |
1 | 4 | 0.45 |
References | Authors | |
16 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Marios Poulos | 1 | 109 | 15.71 |
| George Bokos | 2 | 88 | 7.97 |
| Nikolaos Kanellopoulos | 3 | 12 | 2.15 |
| Sozon Papavlasopoulos | 4 | 21 | 4.79 |
| Markos Avlonitis | 5 | 37 | 10.98 |