Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
NONLINEAR CONTROL OF A LOUDSPEAKER WITH A NEURAL NETWORK
Document Type and Number:
WIPO Patent Application WO/2022/092741
Kind Code:
A1
Abstract:
An electronic device is provided. The electronic device includes a memory storing at least one instruction, and a processor electronically connected with the memory, wherein the processor is configured to, by executing the instruction, input into a first layer of a neural network at least one data sample of a current displacement of one or more moving components of a loudspeaker and at least one or more other data samples of one or more prior displacements of the one or more moving components, generate in the first layer a data vector by applying a nonlinear activation function based on the at least one data sample of the current displacement and the at least one or more other data samples of the one or more prior displacements, input into a second layer of the neural network the data vector and applying an affine transformation to the data vector, and output a prediction of a current voltage to apply to the loudspeaker based on the affine transformation applied to the data vector.

Inventors:
BRUNET PASCAL MAURICE (US)
LI YUAN (US)
Application Number:
PCT/KR2021/015055
Publication Date:
May 05, 2022
Filing Date:
October 26, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
SAMSUNG ELECTRONICS CO LTD (KR)
International Classes:
H04R5/04; G06N3/08; H04R3/00; H04R7/16; H04R9/04; H04R9/06
Foreign References:
US20190222939A12019-07-18
US20150036831A12015-02-05
US20160134982A12016-05-12
US20160345114A12016-11-24
KR101770355B12017-08-22
Other References:
POTIRAKIS S M ET AL., JOURNAL OF THE AUDIO ENGINEERING SOCIETY, AUDIO ENGINEERING SOCIETY, vol. 47, no. 6, 1 June 1999 (1999-06-01)
STEPHEN LOW ET AL.: "A Neural Network Approach to the Adaptive Correction of Loudspeaker Nonlinearities", 95TH AES CONVENTION 3751 (A3-PM-3, 10 October 1993 (1993-10-10)
See also references of EP 4173312A4
Attorney, Agent or Firm:
KIM, Tae-hun et al. (KR)
Download PDF: