PROGRESSIVE MULTI-STAGE NEURAL AUDIO CODING WITH GUIDED REFERENCES

Chanwoo Lee; Hyungseob Lim; Jihyun Lee; Inseon Jang; Hong Goo Kang

doi:10.1109/ICASSP43922.2022.9747527

PROGRESSIVE MULTI-STAGE NEURAL AUDIO CODING WITH GUIDED REFERENCES

Chanwoo Lee, Hyungseob Lim, Jihyun Lee, Inseon Jang, Hong Goo Kang

Department of Electrical and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, we propose an effective multi-stage neural audio coding algorithm that encodes full-band audio signals (up to 20 kHz) using an end-to-end training criterion. By predefining several dyadic subband signals as training targets, we progressively encode input audio signals in each stage such that deeper stages of the network encode the residual error terms from the previous encoding stage. Our proposed audio codec successfully decodes full-band audio signals by using an effective multi-stage vector quantization scheme to represent key encoding features extracted in the latent space. Subjective listening tests show that the decoded outputs of the proposed audio codec achieve almost transparent quality at an average bitrate of 132 kbps.

Original language	English
Title of host publication	2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	876-880
Number of pages	5
ISBN (Electronic)	9781665405409
DOIs	https://doi.org/10.1109/ICASSP43922.2022.9747527
Publication status	Published - 2022
Event	47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Virtual, Online, Singapore Duration: 2022 May 23 → 2022 May 27

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	2022-May
ISSN (Print)	1520-6149

Conference

Conference	47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
Country/Territory	Singapore
City	Virtual, Online
Period	22/5/23 → 22/5/27

Bibliographical note

Funding Information:
This work was supported by Electronics and Telecommunications Research Institute (ETRI) grant funded by the Korean government. [21ZH1200, The research of the basic media contents technologies]

Publisher Copyright:
© 2022 IEEE

All Science Journal Classification (ASJC) codes

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP43922.2022.9747527

Cite this

Lee, C., Lim, H., Lee, J., Jang, I., & Kang, H. G. (2022). PROGRESSIVE MULTI-STAGE NEURAL AUDIO CODING WITH GUIDED REFERENCES. In 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings (pp. 876-880). (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2022-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP43922.2022.9747527

Lee, Chanwoo ; Lim, Hyungseob ; Lee, Jihyun et al. / PROGRESSIVE MULTI-STAGE NEURAL AUDIO CODING WITH GUIDED REFERENCES. 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 876-880 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{0d8b2d4f22134b6cbb23b08ef62d46c8,

title = "PROGRESSIVE MULTI-STAGE NEURAL AUDIO CODING WITH GUIDED REFERENCES",

abstract = "In this paper, we propose an effective multi-stage neural audio coding algorithm that encodes full-band audio signals (up to 20 kHz) using an end-to-end training criterion. By predefining several dyadic subband signals as training targets, we progressively encode input audio signals in each stage such that deeper stages of the network encode the residual error terms from the previous encoding stage. Our proposed audio codec successfully decodes full-band audio signals by using an effective multi-stage vector quantization scheme to represent key encoding features extracted in the latent space. Subjective listening tests show that the decoded outputs of the proposed audio codec achieve almost transparent quality at an average bitrate of 132 kbps.",

author = "Chanwoo Lee and Hyungseob Lim and Jihyun Lee and Inseon Jang and Kang, {Hong Goo}",

note = "Funding Information: This work was supported by Electronics and Telecommunications Research Institute (ETRI) grant funded by the Korean government. [21ZH1200, The research of the basic media contents technologies] Publisher Copyright: {\textcopyright} 2022 IEEE; 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 ; Conference date: 23-05-2022 Through 27-05-2022",

year = "2022",

doi = "10.1109/ICASSP43922.2022.9747527",

language = "English",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "876--880",

booktitle = "2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings",

address = "United States",

}

Lee, C, Lim, H, Lee, J, Jang, I & Kang, HG 2022, PROGRESSIVE MULTI-STAGE NEURAL AUDIO CODING WITH GUIDED REFERENCES. in 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2022-May, Institute of Electrical and Electronics Engineers Inc., pp. 876-880, 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022, Virtual, Online, Singapore, 22/5/23. https://doi.org/10.1109/ICASSP43922.2022.9747527

PROGRESSIVE MULTI-STAGE NEURAL AUDIO CODING WITH GUIDED REFERENCES. / Lee, Chanwoo; Lim, Hyungseob; Lee, Jihyun et al.

2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. p. 876-880 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2022-May).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - PROGRESSIVE MULTI-STAGE NEURAL AUDIO CODING WITH GUIDED REFERENCES

AU - Lee, Chanwoo

AU - Lim, Hyungseob

AU - Lee, Jihyun

AU - Jang, Inseon

AU - Kang, Hong Goo

N1 - Funding Information: This work was supported by Electronics and Telecommunications Research Institute (ETRI) grant funded by the Korean government. [21ZH1200, The research of the basic media contents technologies] Publisher Copyright: © 2022 IEEE

PY - 2022

Y1 - 2022

N2 - In this paper, we propose an effective multi-stage neural audio coding algorithm that encodes full-band audio signals (up to 20 kHz) using an end-to-end training criterion. By predefining several dyadic subband signals as training targets, we progressively encode input audio signals in each stage such that deeper stages of the network encode the residual error terms from the previous encoding stage. Our proposed audio codec successfully decodes full-band audio signals by using an effective multi-stage vector quantization scheme to represent key encoding features extracted in the latent space. Subjective listening tests show that the decoded outputs of the proposed audio codec achieve almost transparent quality at an average bitrate of 132 kbps.

AB - In this paper, we propose an effective multi-stage neural audio coding algorithm that encodes full-band audio signals (up to 20 kHz) using an end-to-end training criterion. By predefining several dyadic subband signals as training targets, we progressively encode input audio signals in each stage such that deeper stages of the network encode the residual error terms from the previous encoding stage. Our proposed audio codec successfully decodes full-band audio signals by using an effective multi-stage vector quantization scheme to represent key encoding features extracted in the latent space. Subjective listening tests show that the decoded outputs of the proposed audio codec achieve almost transparent quality at an average bitrate of 132 kbps.

UR - http://www.scopus.com/inward/record.url?scp=85131255696&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85131255696&partnerID=8YFLogxK

U2 - 10.1109/ICASSP43922.2022.9747527

DO - 10.1109/ICASSP43922.2022.9747527

M3 - Conference contribution

AN - SCOPUS:85131255696

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 876

EP - 880

BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022

Y2 - 23 May 2022 through 27 May 2022

ER -

Lee C, Lim H, Lee J, Jang I, Kang HG. PROGRESSIVE MULTI-STAGE NEURAL AUDIO CODING WITH GUIDED REFERENCES. In 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2022. p. 876-880. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP43922.2022.9747527

PROGRESSIVE MULTI-STAGE NEURAL AUDIO CODING WITH GUIDED REFERENCES

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this