{"id":"https://openalex.org/W3157302296","doi":"https://doi.org/10.1145/3474085.3475323","title":"AMSS-Net: Audio Manipulation on User-Specified Sources with Textual Queries","display_name":"AMSS-Net: Audio Manipulation on User-Specified Sources with Textual Queries","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3157302296","doi":"https://doi.org/10.1145/3474085.3475323","mag":"3157302296"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475323","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475323","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475323","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475323","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102881663","display_name":"Woosung Choi","orcid":"https://orcid.org/0000-0003-2638-2097"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woosung Choi","raw_affiliation_strings":["Korea University, Seoul, Republic of Korea","Korea University , Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Korea University , Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332518","display_name":"Minseok Kim","orcid":"https://orcid.org/0000-0002-3291-5729"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minseok Kim","raw_affiliation_strings":["Korea University, Seoul, Republic of Korea","Korea University , Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Korea University , Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101814826","display_name":"Marco A. Mart\u00ednez Ram\u00edrez","orcid":"https://orcid.org/0000-0002-3989-7519"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marco A. Mart\u00ednez Ram\u00edrez","raw_affiliation_strings":["Queen Mary University of London, London, United Kingdom","Queen-Mary University of London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Queen-Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000577702","display_name":"Jaehwa Chung","orcid":"https://orcid.org/0000-0002-1904-7189"},"institutions":[{"id":"https://openalex.org/I124125349","display_name":"Korea National Open University","ror":"https://ror.org/016ebag96","country_code":"KR","type":"education","lineage":["https://openalex.org/I124125349"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehwa Chung","raw_affiliation_strings":["Korea National Open University, Seoul, Republic of Korea","Korea National Open University, Seoul, Republic of Korea#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea National Open University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I124125349"]},{"raw_affiliation_string":"Korea National Open University, Seoul, Republic of Korea#TAB#","institution_ids":["https://openalex.org/I124125349"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043500102","display_name":"Soonyoung Jung","orcid":"https://orcid.org/0000-0003-2693-9377"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soonyoung Jung","raw_affiliation_strings":["Korea University, Seoul, Republic of Korea","Korea University , Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Korea University , Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03829417,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"1775","last_page":"1783"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.83628249168396},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6930217146873474},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5760245323181152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4366821050643921},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4365793466567993},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34020301699638367}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.83628249168396},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6930217146873474},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5760245323181152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4366821050643921},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4365793466567993},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34020301699638367},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3474085.3475323","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475323","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475323","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.13553","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.13553","pdf_url":"https://arxiv.org/pdf/2104.13553","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2104.13553","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.13553","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3157302296","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1145/3474085.3475323","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475323","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475323","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3157559650","display_name":null,"funder_award_id":"2019R1A6A3A13095526,2020R1A2C1012624,2021R1A2C2011452","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3157302296.pdf","grobid_xml":"https://content.openalex.org/works/W3157302296.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1539749833","https://openalex.org/W2064675550","https://openalex.org/W2097009484","https://openalex.org/W2124479173","https://openalex.org/W2127851351","https://openalex.org/W2131774270","https://openalex.org/W2250539671","https://openalex.org/W2395763828","https://openalex.org/W2550553598","https://openalex.org/W2595181260","https://openalex.org/W2669032454","https://openalex.org/W2725868244","https://openalex.org/W2760103357","https://openalex.org/W2774707525","https://openalex.org/W2897524142","https://openalex.org/W2962793481","https://openalex.org/W2963403868","https://openalex.org/W2963921132","https://openalex.org/W2964121744","https://openalex.org/W2964607787","https://openalex.org/W2969230224","https://openalex.org/W2972162845","https://openalex.org/W2985607490","https://openalex.org/W2991107219","https://openalex.org/W3000145705","https://openalex.org/W3000751478","https://openalex.org/W3015591594","https://openalex.org/W3015753416","https://openalex.org/W3035316078","https://openalex.org/W3043547428","https://openalex.org/W3092775865","https://openalex.org/W3093608541","https://openalex.org/W3093725184","https://openalex.org/W3099024959","https://openalex.org/W3100954996","https://openalex.org/W3122111104","https://openalex.org/W3127566776","https://openalex.org/W4298310324","https://openalex.org/W6691431627"],"related_works":["https://openalex.org/W3205005314","https://openalex.org/W2765345004","https://openalex.org/W1529773983","https://openalex.org/W2756750649","https://openalex.org/W2004489939","https://openalex.org/W1870087433","https://openalex.org/W1576578512","https://openalex.org/W2018675247","https://openalex.org/W3043363188","https://openalex.org/W3206128852","https://openalex.org/W2293964931","https://openalex.org/W1913870715","https://openalex.org/W2072124613","https://openalex.org/W2123041633","https://openalex.org/W3024690827","https://openalex.org/W2987037122","https://openalex.org/W3184264821","https://openalex.org/W3035465116","https://openalex.org/W2010108356","https://openalex.org/W2106620463"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,16,22,37,44,48,66],"neural":[4],"network":[5],"that":[6,104],"performs":[7],"audio":[8,18],"transformations":[9],"to":[10,21,65],"user-specified":[11],"sources":[12,28,82],"(e.g.,":[13],"vocals)":[14],"of":[15],"given":[17,23],"track":[19],"according":[20],"description":[24],"while":[25,87],"preserving":[26,88],"other":[27],"not":[29],"mentioned":[30],"in":[31,63,68],"the":[32],"description.":[33],"Audio":[34],"Manipulation":[35],"on":[36,108],"Specific":[38],"Source":[39],"(AMSS)":[40],"is":[41,54],"challenging":[42,74],"because":[43],"sound":[45],"object":[46],"(i.e.,":[47],"waveform":[49],"sample":[50],"or":[51],"frequency":[52],"bin)":[53],"'transparent';":[55],"it":[56],"usually":[57],"carries":[58],"information":[59],"from":[60],"multiple":[61],"sources,":[62],"contrast":[64],"pixel":[67],"an":[69,94],"image.":[70],"To":[71],"address":[72],"this":[73],"problem,":[75],"we":[76,102],"propose":[77,93],"AMSS-Net,":[78],"which":[79],"extracts":[80],"latent":[81],"and":[83,101,115],"selectively":[84],"manipulates":[85],"them":[86],"irrelevant":[89],"sources.":[90],"We":[91],"also":[92],"evaluation":[95],"benchmark":[96],"for":[97],"several":[98,109],"AMSS":[99,110],"tasks,":[100],"show":[103],"AMSS-Net":[105],"outperforms":[106],"baselines":[107],"tasks":[111],"via":[112],"objective":[113],"metrics":[114],"empirical":[116],"verification.":[117]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
