- 专利标题: METHOD FOR ENCODING AND DECODING AUDIO SIGNAL USING NORMALIZING FLOW, AND TRAINING METHOD THEREOF
-
申请号: US18150126申请日: 2023-01-04
-
公开(公告)号: US20230298603A1公开(公告)日: 2023-09-21
- 发明人: In Seon JANG , Seung Kwon BEACK , Jong Mo SUNG , Tae Jin LEE , Woo Taek LIM , Byeong Ho CHO
- 申请人: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
- 申请人地址: KR Daejeon
- 专利权人: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
- 当前专利权人: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
- 当前专利权人地址: KR Daejeon
- 优先权: KR 20220032180 2022.03.15
- 主分类号: G10L19/032
- IPC分类号: G10L19/032 ; G10L25/30 ; G10L19/04 ; G06N7/01
摘要:
A method for encoding an input signal using N flow blocks (N is a natural number greater than or equal to 2) and (N−1) split block(s), which is performed by a processor, may comprise: transmitting, by a k-th flow block (k is a natural number greater than or equal to 1 and less than or equal to N−1) among the N flow blocks, a k-th transformation signal obtained by transforming a received signal into a latent representation to a k-th split block among the (N−1) split block(s); splitting, by the k-th split block, the k-th transformation signal by a predetermined ratio, into a first split signal and a second split signal; transmitting, by the k-th split block, the first split signal to a (k+1)-th flow block; and quantizing a signal transformed by an N-th flow block and the second split signals using a quantization block.
信息查询