Loudspeaker position identification using human speech directivity index

Celestinos A, Wang CZ, Chin Lopez VM. Loudspeaker position identification using human speech directivity index. In: AES Convention 155. Audio Engineering Society; 2023. Paper 138. Available from: https://aes.org/publications/elibrary-page/?id=22292

@inproceedings{Celestinos2023_22292,
  author = {Celestinos, Adrian and Wang, Carren Zhongran and Chin Lopez, Victor Manuel},
  title = {{Loudspeaker position identification using human speech directivity index}},
  booktitle = {AES Convention 155},
  note = {Paper 138},
  year = {2023},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=22292}
}

TY  - CPAPER
TI  - Loudspeaker position identification using human speech directivity index
AU  - Celestinos, Adrian
AU  - Wang, Carren Zhongran
AU  - Chin Lopez, Victor Manuel
T2  - AES Convention 155
M1  - Paper 138
PY  - 2023
DA  - 2023/10/06
UR  - https://aes.org/publications/elibrary-page/?id=22292
PB  - Audio Engineering Society
LA  - en
AB  - A regular user of a multichannel loudspeaker system in typical living rooms sets the loudspeakers in a non-uniform manner, with angles and distances that don’t necessarily follow the recommended ITU-R BS.2159-4 standard. Assuming a multichannel audio system equipped with N number of loudspeakers and M very near-field (NF) microphones attached to each loudspeaker, the user location with respect to the loudspeakers can be estimated by utilizing a supervised machine learning (ML) model. Two neural networks (NN) were trained with the human speech directivity index (DI) computed by room simulations, where the sound source was the typical directivity radiation pattern of human speech, and the receivers were the NF microphones attached to the loudspeakers. The distances between loudspeakers and the DI data was combined as input for the two NN models. One network was dedicated to estimate distances from loudspeaker to user, and the other network was dedicated to the angle estimation. The results shown a 95% confidence interval (CI) of ±1.7 cm and a CI of ±7 degrees for the incidence angle.
ER  -