음성존재확률 판정방법과 시스템, 음성강화방법과 시스템, 헤드폰

• Main Authors: XIAO LE, LIAO FENGYUN, QI XIN, ZHANG CHENGQIAN
• Format: Patent
• Language: Korean
• Published: 20.07.2023
• Subjects: ACOUSTICS; DEAF-AID SETS; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKEACOUSTIC ELECTROMECHANICAL TRANSDUCERS; MUSICAL INSTRUMENTS; PHYSICS; PUBLIC ADDRESS SYSTEMS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION

본 개시는 음성존재확률을 판정하는 방법과 시스템, 음성강화방법과 시스템, 및 헤드폰을 제공한다. 반복 동작에서 상기 음성존재확률의 엔트로피와 상기 음성부재확률의 엔트로피를 비교함으로써 상기 음성존재확률과 음성부재확률을 수정할 수 있으며, 따라서, 더 빠른 수렴속도와 더 나은 수렴결과를 얻을 수 있으며, 따라서 상기 음성존재확률의 추정의 정확도 및 소음 공간공분산행렬의 추정의 정확도를 개선하고, 최소 평방편차 무왜곡 응답(MVDR)의 음성강화효과를 개선한다. The present disclosure provides a method and system for determining a speech presence probability, a speech enhancement method and system, and a headphone. The speech presence probability and a speech absence probability in an iteration operation may be corrected by comparing an entropy of the speech presence probability and an entropy of a speech absence probability, such that a faster convergence speed and better convergence results may be obtained, thereby improving accuracy of an estimation of the speech presence probability and an accuracy of an estimation of a noise spatial covariance matrix, and then improving a speech enhancement effect of a minimum variance distortionless response (MVDR).