등록
음성신호 압축을 위한 학습가능한 선형예측 계수 양자화 장치 및 방법
- 발명자
-
김민제, 카이 젠, 이미숙, 성종모, 백승권, 이태진, 최진수
- 출원번호
-
17098090 (2020.11.13)
- 공개번호
-
20210142812 (2021.05.13)
- 등록번호
- 11488613 (2022.11.01)
- 출원국
- 미국
- 협약과제
-
19HR2500, [통합과제] 초실감 테라미디어를 위한 AV부호화 및 LF미디어 원천기술 개발,
최진수
- 초록
- Disclosed are a method for coding a residual signal of LPC coefficients based on collaborative quantization and a computing device for performing the method. The residual signal coding method includes: generating encoded LPC coefficients and LPC residual signals by performing LPC analysis and quantization on an input speech; Determining a predicted LPC residual signal by applying the LPC residual signal to cross module residual learning; Performing LPC synthesis using the coded LPC coefficients and the predicted LPC residual signal; It may include the step of determining an output speech that is a synthesized output according to a result of performing the LPC synthesis.
- KSP 제안 키워드
- Coding method, Linear prediction, Prediction coding, Residual coding, Residual signal, Signal Coding, residual learning