Deep Learning for Loudspeaker Digital Twin Creation
×
Cite This
Citation & Abstract
B. Louise, T. Kerimovs, and SE. J.. Schlecht, "Deep Learning for Loudspeaker Digital Twin Creation," Paper 10642, (2023 May.). doi:
B. Louise, T. Kerimovs, and SE. J.. Schlecht, "Deep Learning for Loudspeaker Digital Twin Creation," Paper 10642, (2023 May.). doi:
Abstract: Several studies have used deep learning methods to create digital twins of amps, speakers, and effects pedals. This paper presents a novel method for creating a digital twin of a physical loudspeaker with stereo output. Two neural network architectures are considered: a Recurrent Neural Network (RNN) and a WaveNet-style Convolutional Neural Network (CNN). The models were tested on two datasets containing speech and music, respectively. The method of recording and preprocessing the target audio data addresses the challenge of lacking a direct output line to digitize the effect of nonlinear circuits. Both model architectures successfully create a digital twin of the loudspeaker with no direct output line and stereo audio. The RNN model achieved the best result on the music dataset, while the WaveNet model achieved the best result on the speech dataset.
@article{louise2023deep,
author={louise, bryn and kerimovs, teodors and schlecht, sebastian j.},
journal={journal of the audio engineering society},
title={deep learning for loudspeaker digital twin creation},
year={2023},
volume={},
number={},
pages={},
doi={},
month={may},}
@article{louise2023deep,
author={louise, bryn and kerimovs, teodors and schlecht, sebastian j.},
journal={journal of the audio engineering society},
title={deep learning for loudspeaker digital twin creation},
year={2023},
volume={},
number={},
pages={},
doi={},
month={may},
abstract={several studies have used deep learning methods to create digital twins of amps, speakers, and effects pedals. this paper presents a novel method for creating a digital twin of a physical loudspeaker with stereo output. two neural network architectures are considered: a recurrent neural network (rnn) and a wavenet-style convolutional neural network (cnn). the models were tested on two datasets containing speech and music, respectively. the method of recording and preprocessing the target audio data addresses the challenge of lacking a direct output line to digitize the effect of nonlinear circuits. both model architectures successfully create a digital twin of the loudspeaker with no direct output line and stereo audio. the rnn model achieved the best result on the music dataset, while the wavenet model achieved the best result on the speech dataset.},}
TY - Transducers
TI - Deep Learning for Loudspeaker Digital Twin Creation
SP -
EP -
AU - Louise, Bryn
AU - Kerimovs, Teodors
AU - Schlecht, Sebastian J.
PY - 2023
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2023
TY - Transducers
TI - Deep Learning for Loudspeaker Digital Twin Creation
SP -
EP -
AU - Louise, Bryn
AU - Kerimovs, Teodors
AU - Schlecht, Sebastian J.
PY - 2023
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2023
AB - Several studies have used deep learning methods to create digital twins of amps, speakers, and effects pedals. This paper presents a novel method for creating a digital twin of a physical loudspeaker with stereo output. Two neural network architectures are considered: a Recurrent Neural Network (RNN) and a WaveNet-style Convolutional Neural Network (CNN). The models were tested on two datasets containing speech and music, respectively. The method of recording and preprocessing the target audio data addresses the challenge of lacking a direct output line to digitize the effect of nonlinear circuits. Both model architectures successfully create a digital twin of the loudspeaker with no direct output line and stereo audio. The RNN model achieved the best result on the music dataset, while the WaveNet model achieved the best result on the speech dataset.
Several studies have used deep learning methods to create digital twins of amps, speakers, and effects pedals. This paper presents a novel method for creating a digital twin of a physical loudspeaker with stereo output. Two neural network architectures are considered: a Recurrent Neural Network (RNN) and a WaveNet-style Convolutional Neural Network (CNN). The models were tested on two datasets containing speech and music, respectively. The method of recording and preprocessing the target audio data addresses the challenge of lacking a direct output line to digitize the effect of nonlinear circuits. Both model architectures successfully create a digital twin of the loudspeaker with no direct output line and stereo audio. The RNN model achieved the best result on the music dataset, while the WaveNet model achieved the best result on the speech dataset.
Authors:
Louise, Bryn; Kerimovs, Teodors; Schlecht, Sebastian J.
Affiliations:
Aalto University, Espoo, Finland; Aalto University, Espoo, Finland; Aalto University, Espoo, Finland(See document for exact affiliation information.)
AES Convention:
154 (May 2023)
Paper Number:
10642
Publication Date:
May 13, 2023Import into BibTeX
Subject:
Transducers
Permalink:
http://www.aes.org/e-lib/browse.cfm?elib=22049