Applause detection filter design for remote live-viewing with adaptive modeling filter

Kawahara K, Karakawa M, Omoto A, Kamamoto Y. Applause detection filter design for remote live-viewing with adaptive modeling filter. In: AES Convention 152. Audio Engineering Society; 2022. Paper 675. Available from: https://aes.org/publications/elibrary-page/?id=21736

@inproceedings{Kawahara2022_21736,
  author = {Kawahara, Kazuhiko and Karakawa, Masahiro and Omoto, Akira and Kamamoto, Yutaka},
  title = {{Applause detection filter design for remote live-viewing with adaptive modeling filter}},
  booktitle = {AES Convention 152},
  note = {Paper 675},
  year = {2022},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=21736}
}

TY  - CPAPER
TI  - Applause detection filter design for remote live-viewing with adaptive modeling filter
AU  - Kawahara, Kazuhiko
AU  - Karakawa, Masahiro
AU  - Omoto, Akira
AU  - Kamamoto, Yutaka
T2  - AES Convention 152
M1  - Paper 675
PY  - 2022
DA  - 2022/05/06
UR  - https://aes.org/publications/elibrary-page/?id=21736
PB  - Audio Engineering Society
LA  - en
AB  - The COVID-19 pandemic prevents us from enjoying live performances. On the other hand, commercial audio-visual transmission systems, such as live viewing systems, have become more popular and have been increasing. The APRICOT: (APplause for Realistic Immersive Contents Transmission) system was developed and used in some trials to enhance the reality for live viewing. This paper describes an applause sound extraction method for automation of applause sound transmission and a simulation experiment using the sound source recorded live at the venue to assess the applause sound extraction performance. We used an adaptive filter to model the room transfer function. In addition, we designed the inverse filter to emphasize applause sounds and extracted them. The experimental evaluation showed that the system extracted the applause sounds almost correctly under various conditions from the performance sound source.
ER  -