Abstract | ||
---|---|---|
This paper proposes a solution to the problem of robust speaker localization under adverse acoustic conditions. The approach is based on the classification of time delay estimates. Two classification techniques are investigated in detail: maximum likelihood (ML) classification and classification based on histogram comparison. Their performance under adverse acoustic conditions is compared to outcomes obtained with the traditional approach which uses time delay estimates directly to infer speaker positions. Experiments indicate that the ML classification method provides little improvement over the traditional method. On the other hand, using histogram classification, we can improve the probability of correct speaker localization by more than 60% compared to either the traditional approach or the ML classification technique. |
Year | DOI | Venue |
---|---|---|
1999 | 10.1109/ICASSP.1999.757492 | Acoustics, Speech, and Signal Processing, 1999. Proceedings., 1999 IEEE International Conference |
Keywords | Field | DocType |
acoustic noise,acoustic wave propagation,delay estimation,direction-of-arrival estimation,maximum likelihood estimation,multipath channels,probability,reverberation,signal classification,speech processing,ML classification method,TDOA,acoustic obstructions,adverse acoustic conditions,anechoic chamber,background noise,experiments,histogram classification,histogram comparison,maximum likelihood classification,multipath distortion,performance,probability,reverberations,robust speaker localization,speaker positions,time delay estimates classification | Multipath channels,Noise,Histogram,Speech processing,Reverberation,Acoustic wave propagation,Pattern recognition,Computer science,Maximum likelihood,Speech recognition,Artificial intelligence,Signal classification | Conference |
Volume | ISSN | ISBN |
6 | 1520-6149 | 0-7803-5041-3 |
Citations | PageRank | References |
11 | 2.81 | 4 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Strobel, N. | 1 | 11 | 2.81 |
R. Rabenstein | 2 | 119 | 15.00 |