Name
Abstract | ||
|---|---|---|
A speech enhancementscheme including blind source sepa- ration and background denoising based on minimum statis- tics is studied in mobile environments. To accommodate the dependence of the separated output signals on the spa- tial properties of the recorded source signals, these blind signal processing steps are complemented by an adaptive separated output channel selection stage using prior knowl- edge about the desired speaker speech content. The result- ing scheme performanceis illustrated by speech recognition experiments on real recordings corrupted by various noise sources and shown to outperform conventional beamform- ing and single channel denoising techniques as well as an equivalent scheme with fixed output channel selection. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1109/ICASSP.2004.1326689 | ICASSP '04). IEEE International Conference |
Keywords | Field | DocType |
blind source separation,mobile communication,signal denoising,speech enhancement,speech recognition,statistical analysis,adaptive separated output channel selection,background denoising,blind signal processing,blind source separation,desired speaker speech content,minimum statistics,mobile environments,noise sources,performance,speech enhancement,speech recognition | Speech enhancement,Speech processing,Beamforming,Speech coding,Pattern recognition,Computer science,Voice activity detection,Communication channel,Speech recognition,Artificial intelligence,Blind signal separation,Blind equalization | Conference |
Volume | ISSN | ISBN |
3 | 1520-6149 | 0-7803-8484-9 |
Citations | PageRank | References |
0 | 0.34 | 6 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Erik M. Visser | 1 | 27 | 2.86 |
| Te-Won Lee | 2 | 2233 | 260.51 |