METHOD FOR DECLIPPING AUDIO USING DEEP LEARNING

A method for declipping audio using deep learning according to the present invention comprises: a step of detecting a clipped section in an audio signal for learning; a step of learning a restoration model based on the detected clipped section; and a step of declipping an unidentified audio signal b...

Full description

Saved in:
Bibliographic Details
Main Authors CHOI SEUNG HO, CHOI SEUNG UN
Format Patent
LanguageEnglish
Korean
Published 19.06.2023
Subjects
ACOUSTICS
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
Online AccessGet full text

Cover

More Information
Summary:A method for declipping audio using deep learning according to the present invention comprises: a step of detecting a clipped section in an audio signal for learning; a step of learning a restoration model based on the detected clipped section; and a step of declipping an unidentified audio signal based on the learned restoration model. Therefore, the present invention is capable of shortening a processing time. 본 발명에 따른 딥러닝을 이용하여 오디오를 디클리핑하는 방법은 학습용 오디오 신호에서 클리핑된 구간을 검출하는 단계, 상기 검출된 클리핑된 구간에 기초하여 복원 모델을 학습시키는 단계, 및 상기 학습된 복원 모델에 기초하여 미식별 오디오 신호를 디클리핑하는 단계를 포함한다.
Bibliography:Application Number: KR20220020485