{"id":"https://openalex.org/W2771361008","doi":"https://doi.org/10.1109/waspaa.2017.8170052","title":"Scaper: A library for soundscape synthesis and augmentation","display_name":"Scaper: A library for soundscape synthesis and augmentation","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2771361008","doi":"https://doi.org/10.1109/waspaa.2017.8170052","mag":"2771361008"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2017.8170052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8170052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5037548450","display_name":"Justin Salamon","orcid":"https://orcid.org/0000-0001-6345-4593"},"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":true,"raw_author_name":"Justin Salamon","raw_affiliation_strings":["Center for Urban Science and Progress, New York University, NYC, NY, USA"],"affiliations":[{"raw_affiliation_string":"Center for Urban Science and Progress, New York University, NYC, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038746905","display_name":"Duncan MacConnell","orcid":null},"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":"Duncan MacConnell","raw_affiliation_strings":["New York University, New York, NY, US"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, US","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056532548","display_name":"Mark Cartwright","orcid":"https://orcid.org/0000-0002-5908-390X"},"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":"Mark Cartwright","raw_affiliation_strings":["Music and Audio Research Laboratory, New York University, NYC, NY, USA"],"affiliations":[{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University, NYC, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101839243","display_name":"Peter Li","orcid":"https://orcid.org/0000-0002-2107-3853"},"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":"Peter Li","raw_affiliation_strings":["Music and Audio Research Laboratory, New York University, NYC, NY, USA"],"affiliations":[{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University, NYC, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","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":["Music and Audio Research Laboratory, New York University, NYC, NY, USA"],"affiliations":[{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University, NYC, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037548450"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":10.6282,"has_fulltext":false,"cited_by_count":205,"citation_normalized_percentile":{"value":0.98889267,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"344","last_page":"348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9993000030517578,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9961000084877014,"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/soundscape","display_name":"Soundscape","score":0.9223800897598267},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.8306668400764465},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.770233154296875},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6550048589706421},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.6480538249015808},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5666244626045227},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.48795264959335327},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4807869791984558},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4675976634025574},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.459073543548584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2768527865409851},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20694193243980408},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.20612910389900208},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.1901904046535492},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.09022867679595947},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07265004515647888}],"concepts":[{"id":"https://openalex.org/C142795923","wikidata":"https://www.wikidata.org/wiki/Q1358257","display_name":"Soundscape","level":3,"score":0.9223800897598267},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.8306668400764465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770233154296875},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6550048589706421},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.6480538249015808},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5666244626045227},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.48795264959335327},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4807869791984558},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4675976634025574},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.459073543548584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2768527865409851},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20694193243980408},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.20612910389900208},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.1901904046535492},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.09022867679595947},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07265004515647888},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa.2017.8170052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8170052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.6299999952316284,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332434","display_name":"ExxonMobil Research and Engineering Company","ror":"https://ror.org/01xcepn55"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2385545","https://openalex.org/W87840697","https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W2017282333","https://openalex.org/W2038484192","https://openalex.org/W2101234009","https://openalex.org/W2101298784","https://openalex.org/W2135342008","https://openalex.org/W2137637927","https://openalex.org/W2153331367","https://openalex.org/W2156163116","https://openalex.org/W2159922251","https://openalex.org/W2163605009","https://openalex.org/W2296149406","https://openalex.org/W2398243923","https://openalex.org/W2403438050","https://openalex.org/W2408239454","https://openalex.org/W2471278348","https://openalex.org/W2509065397","https://openalex.org/W2526050071","https://openalex.org/W2552032035","https://openalex.org/W2591013610","https://openalex.org/W2654517624","https://openalex.org/W2774116887","https://openalex.org/W2780407133","https://openalex.org/W2888740332","https://openalex.org/W2914312680","https://openalex.org/W2949117887","https://openalex.org/W2964121744","https://openalex.org/W3098357269","https://openalex.org/W3210141620","https://openalex.org/W4285719527","https://openalex.org/W6603545436","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6675354045","https://openalex.org/W6697229037","https://openalex.org/W6712594816","https://openalex.org/W6713049558","https://openalex.org/W6746715687"],"related_works":["https://openalex.org/W1254698036","https://openalex.org/W3032998312","https://openalex.org/W4384486036","https://openalex.org/W135177976","https://openalex.org/W2896201871","https://openalex.org/W1503094549","https://openalex.org/W1988083194","https://openalex.org/W2282503792","https://openalex.org/W2365709658","https://openalex.org/W1479881079"],"abstract_inverted_index":{"Sound":[0],"event":[1],"detection":[2],"(SED)":[3],"in":[4,13,18,86],"environmental":[5],"recordings":[6],"is":[7,67],"a":[8,73,104,113,122,161,178,203],"key":[9],"topic":[10],"of":[11,31,45,59,106,131,138,156,163,173,205],"research":[12],"machine":[14],"listening,":[15],"with":[16,79,202],"applications":[17],"noise":[19],"monitoring":[20],"for":[21,38,77,98,194],"smart":[22],"cities,":[23],"self-driving":[24],"cars,":[25],"surveillance,":[26],"bioa-coustic":[27],"monitoring,":[28],"and":[29,57,71,84,101,145,166,200,208],"indexing":[30],"large":[32],"multimedia":[33],"collections.":[34],"Developing":[35],"new":[36],"solutions":[37],"SED":[39,78],"often":[40],"relies":[41],"on":[42],"the":[43,51,54,129,132,136,154,157,171],"availability":[44],"strongly":[46],"labeled":[47],"audio":[48,139,192,196],"recordings,":[49],"where":[50],"annotation":[52],"includes":[53],"onset,":[55],"offset":[56],"source":[58],"every":[60,150],"event.":[61,151],"Generating":[62],"such":[63,141],"precise":[64],"annotations":[65],"manually":[66],"very":[68],"time":[69,146],"consuming,":[70],"as":[72,112,142],"result":[74],"existing":[75],"datasets":[76],"strong":[80],"labels":[81],"are":[82],"scarce":[83],"limited":[85],"size.":[87],"To":[88,127,152],"address":[89],"this":[90],"issue,":[91],"we":[92,159],"present":[93],"Scaper,":[94],"an":[95,195],"open-source":[96],"library":[97],"soundscape":[99,181],"synthesis":[100],"augmentation.":[102],"Given":[103],"collection":[105],"iso-lated":[107],"sound":[108],"events,":[109],"Scaper":[110,134,187],"acts":[111],"high-level":[114],"sequencer":[115],"that":[116],"can":[117],"generate":[118,160,191],"multiple":[119],"soundscapes":[120],"from":[121],"single,":[123],"probabilistically":[124],"defined,":[125],"\u201cspecification\u201d.":[126],"increase":[128],"variability":[130],"output,":[133],"supports":[135],"application":[137],"transformations":[140],"pitch":[143],"shifting":[144],"stretching":[147],"individually":[148],"to":[149,169,190],"illustrate":[153],"potential":[155,209],"library,":[158],"dataset":[162],"10,000":[164],"sound-scapes":[165],"use":[167],"it":[168],"compare":[170],"performance":[172],"two":[174],"state-of-the-art":[175],"algorithms,":[176],"including":[177],"breakdown":[179],"by":[180],"characteristics.":[182],"We":[183],"also":[184],"describe":[185],"how":[186],"was":[188],"used":[189],"stimuli":[193],"labeling":[197],"crowdsourcing":[198],"experiment,":[199],"conclude":[201],"discussion":[204],"Scaper's":[206],"limitations":[207],"applications.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":36},{"year":2021,"cited_by_count":37},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
