Use of DNN-Based Beamforming Applied to Different Microphone Array Configurations

Kim TW, Kim NK, Lee GW, Park I, Kim HK. Use of DNN-Based Beamforming Applied to Different Microphone Array Configurations. In: AES Convention 147. Audio Engineering Society; 2019. Paper 10253. Available from: https://aes.org/publications/elibrary-page/?id=20626

@inproceedings{Kim2019_20626,
  author = {Kim, Tae Woo and Kim, Nam Kyun and Lee, Geon Woo and Park, Inyoung and Kim, Hong Kook},
  title = {{Use of DNN-Based Beamforming Applied to Different Microphone Array Configurations}},
  booktitle = {AES Convention 147},
  note = {Paper 10253},
  year = {2019},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=20626}
}

TY  - CPAPER
TI  - Use of DNN-Based Beamforming Applied to Different Microphone Array Configurations
AU  - Kim, Tae Woo
AU  - Kim, Nam Kyun
AU  - Lee, Geon Woo
AU  - Park, Inyoung
AU  - Kim, Hong Kook
T2  - AES Convention 147
M1  - Paper 10253
PY  - 2019
DA  - 2019/10/06
UR  - https://aes.org/publications/elibrary-page/?id=20626
PB  - Audio Engineering Society
LA  - en
AB  - Minimum variance distortionless response (MVDR) beamforming is one of the most popular multichannel signal processing techniques for dereverberation and/or noise reduction. However, the MVDR beamformer has the limitation that it must be designed to be dependent on the receiver array geometry. This paper demonstrates an experimental setup and results by designing a deep learning-based MVDR beamformer and applying it to different microphone array configurations. Consequently, it is shown that the deep learning-based MVDR beamformer provides more robust performance under mismatched microphone array configurations than the conventional statistical MVDR one.
ER  -