WHAT YOU HEAR IS WHAT YOU SEE: AUDIO QUALITY FROM IMAGE QUALITY METRICS

Tashi Namgyal; Alexander Hepburn; Raul Santos-Rodriguez; Valero Laparra; Jesus Malo

WHAT YOU HEAR IS WHAT YOU SEE: AUDIO QUALITY FROM IMAGE QUALITY METRICS

Tashi Namgyal, Alexander Hepburn, Raul Santos-Rodriguez, Valero Laparra, Jesus Malo

Research output: Contribution to conference › Conference Paper › peer-review

Abstract

In this study, we investigate the feasibility of utilizing state-of-the-art perceptual image metrics for evaluating audio signals by representing them as spectrograms. The encouraging outcome of the proposed approach is based on the similarity between the neural mechanisms in the auditory and visual pathways. Furthermore, we customise one of the metrics which has a psychoacoustically plausible architecture to account for the peculiarities of sound signals. We evaluate the effectiveness of our proposed metric and several baseline metrics using a music dataset, with promising results in terms of the correlation between the metrics and the perceived quality of audio as rated by human evaluators.

Original language	English
Pages	367-370
Number of pages	4
Publication status	Published - 7 Sept 2023
Event	26th International Conference on Digital Audio Effects, DAFx 2023 - Copenhagen, Denmark Duration: 4 Sept 2023 → 7 Sept 2023 https://dafx23.create.aau.dk/

Conference

Conference	26th International Conference on Digital Audio Effects, DAFx 2023
Country/Territory	Denmark
City	Copenhagen
Period	4/09/23 → 7/09/23
Internet address	https://dafx23.create.aau.dk/

Bibliographical note

Publisher Copyright:
© 2023 Tashi Namgyal et al.

Access to Document

https://dafx23.create.aau.dk/Licence: CC BY

Handle.net

Persistent link

Cite this

@conference{4f0c5eb4a6af4576aca8b8227a92e91a,

title = "WHAT YOU HEAR IS WHAT YOU SEE: AUDIO QUALITY FROM IMAGE QUALITY METRICS",

abstract = "In this study, we investigate the feasibility of utilizing state-of-the-art perceptual image metrics for evaluating audio signals by representing them as spectrograms. The encouraging outcome of the proposed approach is based on the similarity between the neural mechanisms in the auditory and visual pathways. Furthermore, we customise one of the metrics which has a psychoacoustically plausible architecture to account for the peculiarities of sound signals. We evaluate the effectiveness of our proposed metric and several baseline metrics using a music dataset, with promising results in terms of the correlation between the metrics and the perceived quality of audio as rated by human evaluators.",

author = "Tashi Namgyal and Alexander Hepburn and Raul Santos-Rodriguez and Valero Laparra and Jesus Malo",

note = "Publisher Copyright: {\textcopyright} 2023 Tashi Namgyal et al.; 26th International Conference on Digital Audio Effects, DAFx 2023 ; Conference date: 04-09-2023 Through 07-09-2023",

year = "2023",

month = sep,

day = "7",

language = "English",

pages = "367--370",

url = "https://dafx23.create.aau.dk/",

}

TY - CONF

T1 - WHAT YOU HEAR IS WHAT YOU SEE

T2 - 26th International Conference on Digital Audio Effects, DAFx 2023

AU - Namgyal, Tashi

AU - Hepburn, Alexander

AU - Santos-Rodriguez, Raul

AU - Laparra, Valero

AU - Malo, Jesus

PY - 2023/9/7

Y1 - 2023/9/7

N2 - In this study, we investigate the feasibility of utilizing state-of-the-art perceptual image metrics for evaluating audio signals by representing them as spectrograms. The encouraging outcome of the proposed approach is based on the similarity between the neural mechanisms in the auditory and visual pathways. Furthermore, we customise one of the metrics which has a psychoacoustically plausible architecture to account for the peculiarities of sound signals. We evaluate the effectiveness of our proposed metric and several baseline metrics using a music dataset, with promising results in terms of the correlation between the metrics and the perceived quality of audio as rated by human evaluators.

AB - In this study, we investigate the feasibility of utilizing state-of-the-art perceptual image metrics for evaluating audio signals by representing them as spectrograms. The encouraging outcome of the proposed approach is based on the similarity between the neural mechanisms in the auditory and visual pathways. Furthermore, we customise one of the metrics which has a psychoacoustically plausible architecture to account for the peculiarities of sound signals. We evaluate the effectiveness of our proposed metric and several baseline metrics using a music dataset, with promising results in terms of the correlation between the metrics and the perceived quality of audio as rated by human evaluators.

UR - https://www.scopus.com/pages/publications/85174530179

M3 - Conference Paper

AN - SCOPUS:85174530179

SP - 367

EP - 370

Y2 - 4 September 2023 through 7 September 2023

ER -

WHAT YOU HEAR IS WHAT YOU SEE: AUDIO QUALITY FROM IMAGE QUALITY METRICS

Abstract

Conference

Bibliographical note

Access to Document

Handle.net

Other files and links

Fingerprint

Cite this