AI 3D immersive audio codec based on content-adaptive dynamic down-mixing and up-mixing framework
×
Cite This
Citation & Abstract
WO. HY. Nam, T. Lee, SA. CH. Ko, Y. Son, HY. KW. Chung, K. Kim, J. Kim, S. Hwang, and K. Lee, "AI 3D immersive audio codec based on content-adaptive dynamic down-mixing and up-mixing framework," Paper 10525, (2021 October.). doi:
WO. HY. Nam, T. Lee, SA. CH. Ko, Y. Son, HY. KW. Chung, K. Kim, J. Kim, S. Hwang, and K. Lee, "AI 3D immersive audio codec based on content-adaptive dynamic down-mixing and up-mixing framework," Paper 10525, (2021 October.). doi:
Abstract: Recently, people who prefer to consume media contents via over the top (OTT) platform, such as YouTube, Netflix etc., rather than a conventional broadcasting get increased more and more. To deliver an immersive audio experience to them more effectively, we propose a unified framework for AI-based 3D immersive audio codec. In this framework, to maximize the original immersiveness even at a down-mixed audio, while enabling to precisely reproduce the original 3D audio from the down-mixed audio, content-adaptive dynamic down-mixing and up-mixing scheme is newly proposed. The experimental results show that the proposed framework can render more improved down-mixed audio compared to the conventional method as well as successfully reproduce the original 3D audio.
@article{nam2021ai,
author={nam, woo hyun and lee, tammy and ko, sang chul and son, yoonjae and chung, hyun kwon and kim, kyung-rae and kim, jungkyu and hwang, sunghee and lee, kyunggeun},
journal={journal of the audio engineering society},
title={ai 3d immersive audio codec based on content-adaptive dynamic down-mixing and up-mixing framework},
year={2021},
volume={},
number={},
pages={},
doi={},
month={october},}
@article{nam2021ai,
author={nam, woo hyun and lee, tammy and ko, sang chul and son, yoonjae and chung, hyun kwon and kim, kyung-rae and kim, jungkyu and hwang, sunghee and lee, kyunggeun},
journal={journal of the audio engineering society},
title={ai 3d immersive audio codec based on content-adaptive dynamic down-mixing and up-mixing framework},
year={2021},
volume={},
number={},
pages={},
doi={},
month={october},
abstract={recently, people who prefer to consume media contents via over the top (ott) platform, such as youtube, netflix etc., rather than a conventional broadcasting get increased more and more. to deliver an immersive audio experience to them more effectively, we propose a unified framework for ai-based 3d immersive audio codec. in this framework, to maximize the original immersiveness even at a down-mixed audio, while enabling to precisely reproduce the original 3d audio from the down-mixed audio, content-adaptive dynamic down-mixing and up-mixing scheme is newly proposed. the experimental results show that the proposed framework can render more improved down-mixed audio compared to the conventional method as well as successfully reproduce the original 3d audio.},}
TY - paper
TI - AI 3D immersive audio codec based on content-adaptive dynamic down-mixing and up-mixing framework
SP -
EP -
AU - Nam, Woo Hyun
AU - Lee, Tammy
AU - Ko, Sang Chul
AU - Son, Yoonjae
AU - Chung, Hyun Kwon
AU - Kim, Kyung-Rae
AU - Kim, Jungkyu
AU - Hwang, Sunghee
AU - Lee, Kyunggeun
PY - 2021
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2021
TY - paper
TI - AI 3D immersive audio codec based on content-adaptive dynamic down-mixing and up-mixing framework
SP -
EP -
AU - Nam, Woo Hyun
AU - Lee, Tammy
AU - Ko, Sang Chul
AU - Son, Yoonjae
AU - Chung, Hyun Kwon
AU - Kim, Kyung-Rae
AU - Kim, Jungkyu
AU - Hwang, Sunghee
AU - Lee, Kyunggeun
PY - 2021
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2021
AB - Recently, people who prefer to consume media contents via over the top (OTT) platform, such as YouTube, Netflix etc., rather than a conventional broadcasting get increased more and more. To deliver an immersive audio experience to them more effectively, we propose a unified framework for AI-based 3D immersive audio codec. In this framework, to maximize the original immersiveness even at a down-mixed audio, while enabling to precisely reproduce the original 3D audio from the down-mixed audio, content-adaptive dynamic down-mixing and up-mixing scheme is newly proposed. The experimental results show that the proposed framework can render more improved down-mixed audio compared to the conventional method as well as successfully reproduce the original 3D audio.
Recently, people who prefer to consume media contents via over the top (OTT) platform, such as YouTube, Netflix etc., rather than a conventional broadcasting get increased more and more. To deliver an immersive audio experience to them more effectively, we propose a unified framework for AI-based 3D immersive audio codec. In this framework, to maximize the original immersiveness even at a down-mixed audio, while enabling to precisely reproduce the original 3D audio from the down-mixed audio, content-adaptive dynamic down-mixing and up-mixing scheme is newly proposed. The experimental results show that the proposed framework can render more improved down-mixed audio compared to the conventional method as well as successfully reproduce the original 3D audio.
Authors:
Nam, Woo Hyun; Lee, Tammy; Ko, Sang Chul; Son, Yoonjae; Chung, Hyun Kwon; Kim, Kyung-Rae; Kim, Jungkyu; Hwang, Sunghee; Lee, Kyunggeun
Affiliation:
Samsung Research, Samsung Electronics, Seoul, Republic of Korea
AES Convention:
151 (October 2021)
Paper Number:
10525
Publication Date:
October 13, 2021Import into BibTeX
Subject:
Multichannel and spatial audio processing and applications
Permalink:
http://www.aes.org/e-lib/browse.cfm?elib=21489