Estimation of MVDR Beamforming Weights Based on Deep Neural Network

Jo MJ, Lee GW, Moon JM, Cho C, Kim HK. Estimation of MVDR Beamforming Weights Based on Deep Neural Network. In: AES Convention 145. Audio Engineering Society; 2018. Paper 10068. Available from: https://aes.org/publications/elibrary-page/?id=19794

@inproceedings{Jo2018_19794,
  author = {Jo, Moon Ju and Lee, Geon Woo and Moon, Jung Min and Cho, Choongsang and Kim, Hong Kook},
  title = {{Estimation of MVDR Beamforming Weights Based on Deep Neural Network}},
  booktitle = {AES Convention 145},
  note = {Paper 10068},
  year = {2018},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=19794}
}

TY  - CPAPER
TI  - Estimation of MVDR Beamforming Weights Based on Deep Neural Network
AU  - Jo, Moon Ju
AU  - Lee, Geon Woo
AU  - Moon, Jung Min
AU  - Cho, Choongsang
AU  - Kim, Hong Kook
T2  - AES Convention 145
M1  - Paper 10068
PY  - 2018
DA  - 2018/10/06
UR  - https://aes.org/publications/elibrary-page/?id=19794
PB  - Audio Engineering Society
LA  - en
AB  - In this paper we propose a deep learning-based MVDR beamforming weight estimation method. The MVDR beamforming weight can be estimated based on deep learning using GCC-PHAT without the information on the source location, while the MVDR beamforming weight requires information on the source location. As a result of an experiment with REVERB challenge data, the root mean square error between the estimated weight and the MVDR weight was found to be 0.32.
ER  -