Application of AI techniques for Nonlinear control of loudspeakers
×
Cite This
Citation & Abstract
PA. M.. Brunet, Y. Li, GL. S.. Kubota, and A. Mariajohn, "Application of AI techniques for Nonlinear control of loudspeakers," Paper 10535, (2021 October.). doi:
PA. M.. Brunet, Y. Li, GL. S.. Kubota, and A. Mariajohn, "Application of AI techniques for Nonlinear control of loudspeakers," Paper 10535, (2021 October.). doi:
Abstract: To obtain high loudness, with good bass extension, while keeping distortion low, and ensuring mechanical protection, the motion of the loudspeaker diaphragm needs to be controlled accurately. Actual solutions for nonlinear control of loudspeakers are complex and difficult to implement and tune. They are limited in accuracy due to physical models that do not completely capture the complexity of the loudspeaker. Furthermore, physical model parameters are difficult to estimate.
We present here a novel approach that uses a Neural Network to directly map the diaphragm displacement to the input voltage, allowing us to “invert” the loudspeaker. This technique allows control and linearization of the loudspeaker without theoretical assumptions. It is also simpler to implement.
@article{brunet2021application,
author={brunet, pascal m. and li, yuan and kubota, glenn s. and mariajohn, aaquila},
journal={journal of the audio engineering society},
title={application of ai techniques for nonlinear control of loudspeakers},
year={2021},
volume={},
number={},
pages={},
doi={},
month={october},}
@article{brunet2021application,
author={brunet, pascal m. and li, yuan and kubota, glenn s. and mariajohn, aaquila},
journal={journal of the audio engineering society},
title={application of ai techniques for nonlinear control of loudspeakers},
year={2021},
volume={},
number={},
pages={},
doi={},
month={october},
abstract={to obtain high loudness, with good bass extension, while keeping distortion low, and ensuring mechanical protection, the motion of the loudspeaker diaphragm needs to be controlled accurately. actual solutions for nonlinear control of loudspeakers are complex and difficult to implement and tune. they are limited in accuracy due to physical models that do not completely capture the complexity of the loudspeaker. furthermore, physical model parameters are difficult to estimate.
we present here a novel approach that uses a neural network to directly map the diaphragm displacement to the input voltage, allowing us to “invert” the loudspeaker. this technique allows control and linearization of the loudspeaker without theoretical assumptions. it is also simpler to implement.},}
TY - paper
TI - Application of AI techniques for Nonlinear control of loudspeakers
SP -
EP -
AU - Brunet, Pascal M.
AU - Li, Yuan
AU - Kubota, Glenn S.
AU - Mariajohn, Aaquila
PY - 2021
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2021
TY - paper
TI - Application of AI techniques for Nonlinear control of loudspeakers
SP -
EP -
AU - Brunet, Pascal M.
AU - Li, Yuan
AU - Kubota, Glenn S.
AU - Mariajohn, Aaquila
PY - 2021
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2021
AB - To obtain high loudness, with good bass extension, while keeping distortion low, and ensuring mechanical protection, the motion of the loudspeaker diaphragm needs to be controlled accurately. Actual solutions for nonlinear control of loudspeakers are complex and difficult to implement and tune. They are limited in accuracy due to physical models that do not completely capture the complexity of the loudspeaker. Furthermore, physical model parameters are difficult to estimate.
We present here a novel approach that uses a Neural Network to directly map the diaphragm displacement to the input voltage, allowing us to “invert” the loudspeaker. This technique allows control and linearization of the loudspeaker without theoretical assumptions. It is also simpler to implement.
To obtain high loudness, with good bass extension, while keeping distortion low, and ensuring mechanical protection, the motion of the loudspeaker diaphragm needs to be controlled accurately. Actual solutions for nonlinear control of loudspeakers are complex and difficult to implement and tune. They are limited in accuracy due to physical models that do not completely capture the complexity of the loudspeaker. Furthermore, physical model parameters are difficult to estimate.
We present here a novel approach that uses a Neural Network to directly map the diaphragm displacement to the input voltage, allowing us to “invert” the loudspeaker. This technique allows control and linearization of the loudspeaker without theoretical assumptions. It is also simpler to implement.
Authors:
Brunet, Pascal M.; Li, Yuan; Kubota, Glenn S.; Mariajohn, Aaquila
Affiliation:
Samsung Research America, Valencia, CA, USA
AES Convention:
151 (October 2021)
Paper Number:
10535
Publication Date:
October 13, 2021Import into BibTeX
Subject:
Transducers
Permalink:
http://www.aes.org/e-lib/browse.cfm?elib=21499