Title | ||
---|---|---|
A generic neural acoustic beamforming architecture for robust multi-channel speech processing. |
Abstract | ||
---|---|---|
•Generic robust beamforming approach supported by a neural network.•Microphone array agnostic.•No assumptions on acoustic transfer function.•Robust against noise as well as reverberation.•Achieves state-of-the-art ASR results for CHiME 3 and REVERB.
|
Year | DOI | Venue |
---|---|---|
2017 | 10.1016/j.csl.2016.11.007 | Computer Speech & Language |
Keywords | Field | DocType |
Robust speech recognition,Acoustic beamforming,Multi-channel speech enhancement,Deep neural network | Speech enhancement,Beamforming,Speech processing,Computer science,Convolutional neural network,Voice activity detection,Network architecture,Speech recognition,Time delay neural network,Artificial intelligence,Machine learning,PESQ | Journal |
Volume | Issue | ISSN |
46 | C | 0885-2308 |
Citations | PageRank | References |
3 | 0.42 | 26 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jahn Heymann | 1 | 102 | 10.29 |
Lukas Drude | 2 | 95 | 11.10 |
Reinhold Haeb-Umbach | 3 | 1487 | 211.71 |