{"id":"https://openalex.org/W4386763869","doi":"https://doi.org/10.1109/waspaa58266.2023.10248113","title":"Bridging High-Quality Audio and Video Via Language for Sound Effects Retrieval from Visual Queries","display_name":"Bridging High-Quality Audio and Video Via Language for Sound Effects Retrieval from Visual Queries","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386763869","doi":"https://doi.org/10.1109/waspaa58266.2023.10248113"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113780845","display_name":"Julia Wilkins","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Julia Wilkins","raw_affiliation_strings":["New York University,Music and Audio Research Laboratory,NY,USA","Music and Audio Research Laboratory, New York University, NY, USA","Adobe Research, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"New York University,Music and Audio Research Laboratory,NY,USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University, NY, USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037548450","display_name":"Justin Salamon","orcid":"https://orcid.org/0000-0001-6345-4593"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Salamon","raw_affiliation_strings":["Adobe Research,San Francisco,CA,USA","Adobe Research, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research,San Francisco,CA,USA","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021235229","display_name":"Magdalena Fuentes","orcid":"https://orcid.org/0000-0003-4506-6639"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Magdalena Fuentes","raw_affiliation_strings":["New York University,Music and Audio Research Laboratory,NY,USA","Music and Audio Research Laboratory, New York University, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University,Music and Audio Research Laboratory,NY,USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031398497","display_name":"Juan Pablo Bello","orcid":"https://orcid.org/0000-0001-8561-5204"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Pablo Bello","raw_affiliation_strings":["New York University,Music and Audio Research Laboratory,NY,USA","Music and Audio Research Laboratory, New York University, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University,Music and Audio Research Laboratory,NY,USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110542743","display_name":"Oriol Nieto","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oriol Nieto","raw_affiliation_strings":["Adobe Research,San Francisco,CA,USA","Adobe Research, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research,San Francisco,CA,USA","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113780845"],"corresponding_institution_ids":["https://openalex.org/I1306409833","https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":0.8151,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72125196,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9930999875068665,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9763000011444092,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8666318655014038},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7186346650123596},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5005025863647461},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4893893599510193},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.47987642884254456},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4224185347557068},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4202570617198944},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39467114210128784},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3763173222541809},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34761863946914673},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3267401456832886},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.2102583348751068},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19382897019386292},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.16043579578399658}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8666318655014038},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7186346650123596},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5005025863647461},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4893893599510193},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.47987642884254456},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4224185347557068},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4202570617198944},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39467114210128784},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3763173222541809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34761863946914673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3267401456832886},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2102583348751068},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19382897019386292},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.16043579578399658},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa58266.2023.10248113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2184188583","https://openalex.org/W2226147954","https://openalex.org/W2593116425","https://openalex.org/W2767290858","https://openalex.org/W2964109005","https://openalex.org/W3005680577","https://openalex.org/W3015371781","https://openalex.org/W3094550259","https://openalex.org/W3114632476","https://openalex.org/W3158553615","https://openalex.org/W3166396011","https://openalex.org/W3176445421","https://openalex.org/W3198377975","https://openalex.org/W3198668032","https://openalex.org/W3205786327","https://openalex.org/W4206677874","https://openalex.org/W4225769111","https://openalex.org/W4248890166","https://openalex.org/W4284898017","https://openalex.org/W4297808394","https://openalex.org/W4310230601","https://openalex.org/W4311642023","https://openalex.org/W4312319752","https://openalex.org/W4312393956","https://openalex.org/W4312864639","https://openalex.org/W4313190371","https://openalex.org/W4318351475","https://openalex.org/W4372260310","https://openalex.org/W4375869234","https://openalex.org/W4386076057","https://openalex.org/W6686207219","https://openalex.org/W6774314701","https://openalex.org/W6791353385","https://openalex.org/W6811331202","https://openalex.org/W6844194202","https://openalex.org/W6846849257","https://openalex.org/W6847019931","https://openalex.org/W6847118041","https://openalex.org/W6849105126"],"related_works":["https://openalex.org/W1992807924","https://openalex.org/W2062427795","https://openalex.org/W2360553097","https://openalex.org/W2354642172","https://openalex.org/W2172869578","https://openalex.org/W2020540721","https://openalex.org/W2578916128","https://openalex.org/W2015950787","https://openalex.org/W2368779261","https://openalex.org/W3086385519"],"abstract_inverted_index":{"Finding":[0],"the":[1,22,39,46,62,85,91,107,197,207,225,238,255,259,273],"right":[2],"sound":[3],"effects":[4],"(SFX)":[5],"to":[6,56,61,106,113,142,148,170,210,212,221,271,291,293],"match":[7],"moments":[8],"in":[9,153],"a":[10,13,34,53,121,129,154,172,228],"video":[11,35,92,130,147],"is":[12,41,87,99],"difficult":[14],"and":[15,18,24,51,90,138,146,162,167,264,277,294],"time-consuming":[16],"task,":[17,214],"relies":[19,74],"heavily":[20],"on":[21,48,71,75,193,196,227,237,282],"quality":[23,81],"completeness":[25],"of":[26,64,79,93,109,199,230,258,275],"text":[27,49],"metadata.":[28],"Retrieving":[29],"high-quality":[30],"(HQ)":[31],"SFX":[32,127,201,249,297],"using":[33,164,183],"frame":[36,131],"directly":[37],"as":[38],"query":[40],"an":[42],"attractive":[43],"alternative,":[44],"removing":[45],"reliance":[47],"metadata":[50],"providing":[52],"low":[54],"barrier":[55],"entry":[57],"for":[58,82,124,203,262],"non-experts.":[59],"Due":[60],"lack":[63],"HQ":[65,111,126,144,200,239,263],"audiovisual":[66],"training":[67],"data,":[68,223],"previous":[69],"work":[70],"audio-visual":[72,150,158,240],"retrieval":[73,175,202,284,298],"YouTube":[76,231],"(\"in-the-wild\")":[77],"videos":[78,232],"varied":[80],"training,":[83],"where":[84],"audio":[86,112,145,166],"often":[88],"noisy":[89],"amateur":[94],"quality.":[95],"As":[96],"such":[97],"it":[98],"unclear":[100],"whether":[101],"these":[102],"systems":[103],"would":[104],"generalize":[105,211],"task":[108,198],"matching":[110],"production-quality":[114],"video.":[115,204],"To":[116],"address":[117],"this,":[118],"we":[119,268],"propose":[120],"multimodal":[122],"framework":[123],"recommending":[125],"given":[128],"by":[132,251],"(1)":[133],"leveraging":[134],"large":[135],"language":[136],"models":[137,141],"foundational":[139],"vision-language":[140],"bridge":[143],"create":[149],"pairs,":[151],"resulting":[152],"highly":[155],"scalable":[156],"automatic":[157,185],"data":[159,186,195,278],"curation":[160,187],"pipeline;":[161],"(2)":[163],"pre-trained":[165],"visual":[168],"encoders":[169],"train":[171],"contrastive":[173],"learning-based":[174],"system.":[176],"We":[177],"show":[178],"that":[179,246],"our":[180,184,215,252,288,296],"system,":[181],"trained":[182,192,236],"pipeline,":[188],"significantly":[189],"outperforms":[190],"baselines":[191,208,226],"in-the-wild":[194,222,265],"Furthermore,":[205],"while":[206],"fail":[209],"this":[213],"system":[216,253],"generalizes":[217],"well":[218],"from":[219],"clean":[220],"outperforming":[224],"dataset":[229],"despite":[233],"only":[234],"being":[235],"pairs.":[241],"A":[242],"user":[243],"study":[244],"confirms":[245],"people":[247],"prefer":[248],"retrieved":[250],"over":[254],"baseline":[256],"67%":[257],"time":[260],"both":[261],"data.":[266],"Finally,":[267],"present":[269],"ablations":[270],"determine":[272],"impact":[274],"model":[276],"pipeline":[279],"design":[280],"choices":[281],"downstream":[283],"performance.":[285],"Please":[286],"visit":[287],"companion":[289],"website":[290],"listen":[292],"view":[295],"results.":[299]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
