US 11,783,844 B2
Methods of encoding and decoding audio signal using side information, and encoder and decoder for performing the methods
Woo-taek Lim, Sejong-si (KR); Seung Kwon Beack, Daejeon (KR); Jongmo Sung, Daejeon (KR); Tae Jin Lee, Daejeon (KR); Inseon Jang, Daejeon (KR); Jong Won Shin, Gwangju (KR); Soojoong Hwang, Gwangju (KR); Youngju Cheon, Gwangju (KR); and Sangwook Han, Gwangju (KR)
Assigned to ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, Daejeon (KR); and GWANGJU INSTITUTE OF SCIENCE AND TECHNOLOGY, Gwangju (KR)
Filed by ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, Daejeon (KR); and Gwangju Institute of Science and Technology, Gwangju (KR)
Filed on Nov. 16, 2021, as Appl. No. 17/527,351.
Claims priority of application No. 10-2021-0059312 (KR), filed on May 7, 2021.
Prior Publication US 2022/0358940 A1, Nov. 10, 2022
Int. Cl. G10L 17/02 (2013.01); G10L 21/00 (2013.01); G10L 19/00 (2013.01); G10L 19/02 (2013.01); G10L 25/30 (2013.01); G10L 25/21 (2013.01); G06N 3/045 (2023.01)
CPC G10L 19/02 (2013.01) [G06N 3/045 (2023.01); G10L 25/21 (2013.01); G10L 25/30 (2013.01)] 6 Claims
OG exemplary drawing
 
1. A method of encoding an audio signal using side information, the method comprising:
identifying an input signal, the input signal being an original audio signal;
extracting side information from the input signal using a learning model trained to extract side information from a feature vector of the input signal;
encoding the input signal; and
generating a bitstream by combining the encoded input signal and the side information,
wherein the side information comprises information on energy of a low-band signal with a frequency less than or equal to a criterion, in the input signal.