US 12,277,951 B2
Beamforming method using online likelihood maximization combined with steering vector estimation for robust speech recognition, and apparatus therefor
Hyung Min Park, Seoul (KR); and Byung Joon Cho, Seoul (KR)
Assigned to MPWAV INC., Seoul (KR)
Appl. No. 17/921,074
Filed by MPWAV INC., Seoul (KR)
PCT Filed May 7, 2021, PCT No. PCT/KR2021/005759
§ 371(c)(1), (2) Date Oct. 24, 2022,
PCT Pub. No. WO2021/235750, PCT Pub. Date Nov. 25, 2021.
Claims priority of application No. 10-2020-0058882 (KR), filed on May 18, 2020.
Prior Publication US 2023/0178089 A1, Jun. 8, 2023
Int. Cl. G10L 21/0208 (2013.01); G10L 21/0216 (2013.01)
CPC G10L 21/0208 (2013.01) [G10L 2021/02082 (2013.01); G10L 2021/02166 (2013.01)] 12 Claims
OG exemplary drawing
 
1. A target signal extraction apparatus comprising:
a steering vector estimator generating an input signal covariance according to input results for each frequency over time, generating a noise covariance based on a variance determined according to output results corresponding to the input results, and generating a steering vector based on the input signal covariance and the noise covariance; and
a beamformer generating a beamforming weight according to a beamforming covariance determined according to the variance and the steering vector, and providing the output results based on the input results and the beamforming weight.