Beamforming method and beamforming system using neural network
Provided are a beamforming method and a beamforming system. The beamforming method may comprise the steps of: receiving a first sound signal and a second sound signal by respectively using a first microphone and a second microphone spaced apart from the first microphone by a pre-determined distance; obtaining a Fourier transform result for each of the first sound signal and the second sound signal; obtaining a phase difference between the first sound signal and the second sound signal from the Fourier transform result; performing an arithmetic operation by inputting the phase difference to a beamforming model by using a neural network; performing element multiplication on an operation result of the neural processor and the Fourier transform result for the first sound signal; and outputting a result of the element multiplication.
1 . A beamforming method, comprising the steps of:
receiving, respectively, a first sound signal and a second sound signal using a first microphone and a second microphone disposed apart from the first microphone by a predetermined distance;
obtaining Fourier transform results for the first sound signal and the second sound signal, respectively;
acquiring a phase difference between the first sound signal and the second sound signal from the Fourier transform results;
inputting only the phase difference into a beamforming model and performing neural network operations using a neural processor, wherein the neural processor performs the beamforming method independently or together with a processor that performs overall control of a beamforming device, and wherein the beamforming model is trained to perform the neural network operations based only on the phase difference;
performing element-wise multiplication between corresponding components of a matrix representing an output of the neural network operations and a matrix representing the Fourier transform results for the first sound signal; and
outputting the element-wise multiplication results,
wherein the neural processor obtains a mask using a Soft Binary Mask (SBM) method through the neural network operations.
2 . The beamforming method of claim 1 , wherein
the predetermined distance is within a range of 10 cm to 14.
3 . The beamforming method of claim 1 ,
further comprising a step of training the beamforming model using the phase difference.
4 . A beamforming system, comprising:
a first microphone for receiving a first sound signal;
a second microphone disposed apart from the first microphone by a predetermined distance to receive a second sound signal;
a processor configured to obtain Fourier transform results for the first sound signal and Fourier transform results for the second sound signal, and to acquire a phase difference between the first sound signal and the second sound signal from the result of the Fourier transform; and
a neural processor configured to perform neural network operations using only the phase difference as input, with a beamforming model, wherein the neural processor performs the beamforming method independently or together with the processor that performs overall control of a beamforming device, and wherein the beamforming model is trained to perform the neural network operations based only on the phase difference,
wherein the processor performs element-wise multiplication between corresponding components of a matrix representing an output of the neural network operations and a matrix representing the Fourier transform results for the first sound signal and outputs the result of the element-wise multiplication,
wherein the neural processor obtains a mask using a Soft Binary Mask (SBM) method through the neural network operations.
5 . The beamforming system of claim 4 , wherein
the predetermined distance is between 10 cm and 14 cm.
6 . The beamforming system of claim 4 , further comprising:
a learning model for training the beamforming model using the phase difference.