Environment Transfer for Distributed Systems

Collecting sufficient amount of data that can represent various acoustic environmental attributes is a critical problem for distributed acoustic machine learning. Several audio data augmentation techniques have been introduced to address this problem but they tend to remain in simple manipulation of...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jiang, Chunheng, Ahn, Jae-wook, Desai, Nirmit
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Jiang, Chunheng
Ahn, Jae-wook
Desai, Nirmit
description Collecting sufficient amount of data that can represent various acoustic environmental attributes is a critical problem for distributed acoustic machine learning. Several audio data augmentation techniques have been introduced to address this problem but they tend to remain in simple manipulation of existing data and are insufficient to cover the variability of the environments. We propose a method to extend a technique that has been used for transferring acoustic style textures between audio data. The method transfers audio signatures between environments for distributed acoustic data augmentation. This paper devises metrics to evaluate the generated acoustic data, based on classification accuracy and content preservation. A series of experiments were conducted using UrbanSound8K dataset and the results show that the proposed method generates better audio data with transferred environmental features while preserving content features.
doi_str_mv 10.48550/arxiv.2101.01863
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2101_01863</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2101_01863</sourcerecordid><originalsourceid>FETCH-LOGICAL-a673-d542da63e06f8c568c8126d10096dbb5199a4ce67009373b8b19f0c6eb24f6623</originalsourceid><addsrcrecordid>eNotzrsKwjAYhuEsDqJegJO9AFtzaP6mo9QjFBzsXpImgYCtktSid-9x-uAdPh6E5gQnqeAcr6R_uCGhBJMEEwFsjJbbbnD-2rWm66PKyy5Y4yN79dHGhd47de-Njs7P0Js2TNHIyksws_9OULXbVsUhLk_7Y7EuYwkZizVPqZbADAYrGg6iEYSCJhjnoJXiJM9l2hjI3oFlTAlFcosbMIqmFoCyCVr8br_c-uZdK_2z_rDrL5u9ACUWPDI</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Environment Transfer for Distributed Systems</title><source>arXiv.org</source><creator>Jiang, Chunheng ; Ahn, Jae-wook ; Desai, Nirmit</creator><creatorcontrib>Jiang, Chunheng ; Ahn, Jae-wook ; Desai, Nirmit</creatorcontrib><description>Collecting sufficient amount of data that can represent various acoustic environmental attributes is a critical problem for distributed acoustic machine learning. Several audio data augmentation techniques have been introduced to address this problem but they tend to remain in simple manipulation of existing data and are insufficient to cover the variability of the environments. We propose a method to extend a technique that has been used for transferring acoustic style textures between audio data. The method transfers audio signatures between environments for distributed acoustic data augmentation. This paper devises metrics to evaluate the generated acoustic data, based on classification accuracy and content preservation. A series of experiments were conducted using UrbanSound8K dataset and the results show that the proposed method generates better audio data with transferred environmental features while preserving content features.</description><identifier>DOI: 10.48550/arxiv.2101.01863</identifier><language>eng</language><subject>Computer Science - Learning ; Computer Science - Sound</subject><creationdate>2021-01</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2101.01863$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2101.01863$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Jiang, Chunheng</creatorcontrib><creatorcontrib>Ahn, Jae-wook</creatorcontrib><creatorcontrib>Desai, Nirmit</creatorcontrib><title>Environment Transfer for Distributed Systems</title><description>Collecting sufficient amount of data that can represent various acoustic environmental attributes is a critical problem for distributed acoustic machine learning. Several audio data augmentation techniques have been introduced to address this problem but they tend to remain in simple manipulation of existing data and are insufficient to cover the variability of the environments. We propose a method to extend a technique that has been used for transferring acoustic style textures between audio data. The method transfers audio signatures between environments for distributed acoustic data augmentation. This paper devises metrics to evaluate the generated acoustic data, based on classification accuracy and content preservation. A series of experiments were conducted using UrbanSound8K dataset and the results show that the proposed method generates better audio data with transferred environmental features while preserving content features.</description><subject>Computer Science - Learning</subject><subject>Computer Science - Sound</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzrsKwjAYhuEsDqJegJO9AFtzaP6mo9QjFBzsXpImgYCtktSid-9x-uAdPh6E5gQnqeAcr6R_uCGhBJMEEwFsjJbbbnD-2rWm66PKyy5Y4yN79dHGhd47de-Njs7P0Js2TNHIyksws_9OULXbVsUhLk_7Y7EuYwkZizVPqZbADAYrGg6iEYSCJhjnoJXiJM9l2hjI3oFlTAlFcosbMIqmFoCyCVr8br_c-uZdK_2z_rDrL5u9ACUWPDI</recordid><startdate>20210105</startdate><enddate>20210105</enddate><creator>Jiang, Chunheng</creator><creator>Ahn, Jae-wook</creator><creator>Desai, Nirmit</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20210105</creationdate><title>Environment Transfer for Distributed Systems</title><author>Jiang, Chunheng ; Ahn, Jae-wook ; Desai, Nirmit</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a673-d542da63e06f8c568c8126d10096dbb5199a4ce67009373b8b19f0c6eb24f6623</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Learning</topic><topic>Computer Science - Sound</topic><toplevel>online_resources</toplevel><creatorcontrib>Jiang, Chunheng</creatorcontrib><creatorcontrib>Ahn, Jae-wook</creatorcontrib><creatorcontrib>Desai, Nirmit</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Jiang, Chunheng</au><au>Ahn, Jae-wook</au><au>Desai, Nirmit</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Environment Transfer for Distributed Systems</atitle><date>2021-01-05</date><risdate>2021</risdate><abstract>Collecting sufficient amount of data that can represent various acoustic environmental attributes is a critical problem for distributed acoustic machine learning. Several audio data augmentation techniques have been introduced to address this problem but they tend to remain in simple manipulation of existing data and are insufficient to cover the variability of the environments. We propose a method to extend a technique that has been used for transferring acoustic style textures between audio data. The method transfers audio signatures between environments for distributed acoustic data augmentation. This paper devises metrics to evaluate the generated acoustic data, based on classification accuracy and content preservation. A series of experiments were conducted using UrbanSound8K dataset and the results show that the proposed method generates better audio data with transferred environmental features while preserving content features.</abstract><doi>10.48550/arxiv.2101.01863</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2101.01863
ispartof
issn
language eng
recordid cdi_arxiv_primary_2101_01863
source arXiv.org
subjects Computer Science - Learning
Computer Science - Sound
title Environment Transfer for Distributed Systems
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-26T20%3A53%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Environment%20Transfer%20for%20Distributed%20Systems&rft.au=Jiang,%20Chunheng&rft.date=2021-01-05&rft_id=info:doi/10.48550/arxiv.2101.01863&rft_dat=%3Carxiv_GOX%3E2101_01863%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true