SocialFX: Studying a crowdsourced folksonomy of audio effects terms

Taylor Zheng; Prem Seetharaman; Bryan A Pardo

doi:10.1145/2964284.2967207

SocialFX: Studying a crowdsourced folksonomy of audio effects terms

Taylor Zheng, Prem Seetharaman, Bryan A Pardo

Computer Science

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

11 Scopus citations

Abstract

We present the analysis of crowdsourced studies into how a population of Amazon Mechanical Turk Workers describe three commonly used audio effiects: equalization, reverberation, and dynamic range compression. We find three categories of words used to describe audio: ones that are generally used across effiects, ones that tend towards a single effect, and ones that are exclusive to a single effect. We present select examples from these categories. We visualize and present an analysis of the shared descriptor space between audio effiects. Data on the strength of association between words and effiects is made available online for a set of 4297 words drawn from 1233 unique users for three effiects (equalization, reverberation, compression). This dataset is an important step towards implementing of an end-to-end language-based audio production system, in which a user describes a creative goal, as they would to a professional audio engineer, and the system picks which audio effect to apply, as well as the setting of the audio effect.

Original language	English (US)
Title of host publication	MM 2016 - Proceedings of the 2016 ACM Multimedia Conference
Publisher	Association for Computing Machinery, Inc
Pages	182-186
Number of pages	5
ISBN (Electronic)	9781450336031
DOIs	https://doi.org/10.1145/2964284.2967207
State	Published - Oct 1 2016
Event	24th ACM Multimedia Conference, MM 2016 - Amsterdam, United Kingdom Duration: Oct 15 2016 → Oct 19 2016

Publication series

Name	MM 2016 - Proceedings of the 2016 ACM Multimedia Conference

Other

Other	24th ACM Multimedia Conference, MM 2016
Country/Territory	United Kingdom
City	Amsterdam
Period	10/15/16 → 10/19/16

Funding

We would like to thank NSF Grants 1116384 and 1420971 for funding this work. Thanks to Alison Wahl for providing source audio for SocialFX.

Keywords

Audio engineering
Compression
Crowdsourcing
Effects processing
Equalization
Interfaces
Reverberation
Signal processing
Vocabulary

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Human-Computer Interaction
Computer Vision and Pattern Recognition
Software

Access to Document

10.1145/2964284.2967207

Cite this

@inproceedings{7f5ac59259b540198d59145f3c7ea74b,

title = "SocialFX: Studying a crowdsourced folksonomy of audio effects terms",

abstract = "We present the analysis of crowdsourced studies into how a population of Amazon Mechanical Turk Workers describe three commonly used audio effiects: equalization, reverberation, and dynamic range compression. We find three categories of words used to describe audio: ones that are generally used across effiects, ones that tend towards a single effect, and ones that are exclusive to a single effect. We present select examples from these categories. We visualize and present an analysis of the shared descriptor space between audio effiects. Data on the strength of association between words and effiects is made available online for a set of 4297 words drawn from 1233 unique users for three effiects (equalization, reverberation, compression). This dataset is an important step towards implementing of an end-to-end language-based audio production system, in which a user describes a creative goal, as they would to a professional audio engineer, and the system picks which audio effect to apply, as well as the setting of the audio effect.",

keywords = "Audio engineering, Compression, Crowdsourcing, Effects processing, Equalization, Interfaces, Reverberation, Signal processing, Vocabulary",

author = "Taylor Zheng and Prem Seetharaman and Pardo, \{Bryan A\}",

note = "Publisher Copyright: {\textcopyright} 2016 ACM.; 24th ACM Multimedia Conference, MM 2016 ; Conference date: 15-10-2016 Through 19-10-2016",

year = "2016",

month = oct,

day = "1",

doi = "10.1145/2964284.2967207",

language = "English (US)",

series = "MM 2016 - Proceedings of the 2016 ACM Multimedia Conference",

publisher = "Association for Computing Machinery, Inc",

pages = "182--186",

booktitle = "MM 2016 - Proceedings of the 2016 ACM Multimedia Conference",

}

Zheng, T, Seetharaman, P & Pardo, BA 2016, SocialFX: Studying a crowdsourced folksonomy of audio effects terms. in MM 2016 - Proceedings of the 2016 ACM Multimedia Conference. MM 2016 - Proceedings of the 2016 ACM Multimedia Conference, Association for Computing Machinery, Inc, pp. 182-186, 24th ACM Multimedia Conference, MM 2016, Amsterdam, United Kingdom, 10/15/16. https://doi.org/10.1145/2964284.2967207

SocialFX: Studying a crowdsourced folksonomy of audio effects terms. / Zheng, Taylor; Seetharaman, Prem; Pardo, Bryan A.
MM 2016 - Proceedings of the 2016 ACM Multimedia Conference. Association for Computing Machinery, Inc, 2016. p. 182-186 (MM 2016 - Proceedings of the 2016 ACM Multimedia Conference).

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

TY - GEN

T1 - SocialFX

T2 - 24th ACM Multimedia Conference, MM 2016

AU - Zheng, Taylor

AU - Seetharaman, Prem

AU - Pardo, Bryan A

PY - 2016/10/1

Y1 - 2016/10/1

N2 - We present the analysis of crowdsourced studies into how a population of Amazon Mechanical Turk Workers describe three commonly used audio effiects: equalization, reverberation, and dynamic range compression. We find three categories of words used to describe audio: ones that are generally used across effiects, ones that tend towards a single effect, and ones that are exclusive to a single effect. We present select examples from these categories. We visualize and present an analysis of the shared descriptor space between audio effiects. Data on the strength of association between words and effiects is made available online for a set of 4297 words drawn from 1233 unique users for three effiects (equalization, reverberation, compression). This dataset is an important step towards implementing of an end-to-end language-based audio production system, in which a user describes a creative goal, as they would to a professional audio engineer, and the system picks which audio effect to apply, as well as the setting of the audio effect.

AB - We present the analysis of crowdsourced studies into how a population of Amazon Mechanical Turk Workers describe three commonly used audio effiects: equalization, reverberation, and dynamic range compression. We find three categories of words used to describe audio: ones that are generally used across effiects, ones that tend towards a single effect, and ones that are exclusive to a single effect. We present select examples from these categories. We visualize and present an analysis of the shared descriptor space between audio effiects. Data on the strength of association between words and effiects is made available online for a set of 4297 words drawn from 1233 unique users for three effiects (equalization, reverberation, compression). This dataset is an important step towards implementing of an end-to-end language-based audio production system, in which a user describes a creative goal, as they would to a professional audio engineer, and the system picks which audio effect to apply, as well as the setting of the audio effect.

KW - Audio engineering

KW - Compression

KW - Crowdsourcing

KW - Effects processing

KW - Equalization

KW - Interfaces

KW - Reverberation

KW - Signal processing

KW - Vocabulary

UR - http://www.scopus.com/inward/record.url?scp=84994613824&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84994613824&partnerID=8YFLogxK

U2 - 10.1145/2964284.2967207

DO - 10.1145/2964284.2967207

M3 - Conference contribution

AN - SCOPUS:84994613824

T3 - MM 2016 - Proceedings of the 2016 ACM Multimedia Conference

SP - 182

EP - 186

BT - MM 2016 - Proceedings of the 2016 ACM Multimedia Conference

PB - Association for Computing Machinery, Inc

Y2 - 15 October 2016 through 19 October 2016

ER -

SocialFX: Studying a crowdsourced folksonomy of audio effects terms

Abstract

Publication series

Other

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this