{"id":"https://openalex.org/W3162139346","doi":"https://doi.org/10.1109/waspaa52581.2021.9632767","title":"Weakly Supervised Source-Specific Sound Level Estimation in Noisy Soundscapes","display_name":"Weakly Supervised Source-Specific Sound Level Estimation in Noisy Soundscapes","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3162139346","doi":"https://doi.org/10.1109/waspaa52581.2021.9632767","mag":"3162139346"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa52581.2021.9632767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"preprint","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/A5045867725","display_name":"Aurora Cramer","orcid":"https://orcid.org/0000-0001-5288-9399"},"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":"Aurora Cramer","raw_affiliation_strings":["New York University, Music and Audio Research Laboratory, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, Music and Audio Research Laboratory, New York, NY, USA","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/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Cartwright","raw_affiliation_strings":["New Jersey Institute of Technology, Newark, NJ, USA"],"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072149059","display_name":"Fatemeh Pishdadian","orcid":null},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fatemeh Pishdadian","raw_affiliation_strings":["Northwestern University, Evanston, IL, USA"],"affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"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":["New York University, Music and Audio Research Laboratory, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, Music and Audio Research Laboratory, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045867725"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":0.28795905,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52201173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"65"},"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":0.9998000264167786,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8010597229003906},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7528177499771118},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6423682570457458},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4866202771663666},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.47509944438934326},{"id":"https://openalex.org/keywords/soundscape","display_name":"Soundscape","score":0.4692687392234802},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.461515873670578},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4087284207344055},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36236876249313354},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.3619748651981354},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3329400420188904},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1792280077934265}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8010597229003906},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7528177499771118},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6423682570457458},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4866202771663666},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.47509944438934326},{"id":"https://openalex.org/C142795923","wikidata":"https://www.wikidata.org/wiki/Q1358257","display_name":"Soundscape","level":3,"score":0.4692687392234802},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.461515873670578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4087284207344055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36236876249313354},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.3619748651981354},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3329400420188904},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1792280077934265},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa52581.2021.9632767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1549884461","https://openalex.org/W2005933202","https://openalex.org/W2038484192","https://openalex.org/W2130838500","https://openalex.org/W2153331367","https://openalex.org/W2161071682","https://openalex.org/W2530495859","https://openalex.org/W2759976799","https://openalex.org/W2762206788","https://openalex.org/W2771361008","https://openalex.org/W2798158991","https://openalex.org/W2810934215","https://openalex.org/W2883567977","https://openalex.org/W2892511205","https://openalex.org/W2912056372","https://openalex.org/W2918296821","https://openalex.org/W2939574508","https://openalex.org/W2964058413","https://openalex.org/W2964136284","https://openalex.org/W2981733351","https://openalex.org/W2982449249","https://openalex.org/W2984935418","https://openalex.org/W3004910802","https://openalex.org/W3036069164","https://openalex.org/W3104704316","https://openalex.org/W3123940584","https://openalex.org/W3169359258","https://openalex.org/W4205298730","https://openalex.org/W4256604311","https://openalex.org/W6727915769","https://openalex.org/W6744586407","https://openalex.org/W6796637347","https://openalex.org/W6912976838"],"related_works":["https://openalex.org/W1254698036","https://openalex.org/W2896201871","https://openalex.org/W2282503792","https://openalex.org/W1608003482","https://openalex.org/W2903040254","https://openalex.org/W2074134755","https://openalex.org/W4226449293","https://openalex.org/W2943743938","https://openalex.org/W2129566906","https://openalex.org/W2117408192"],"abstract_inverted_index":{"While":[0],"the":[1,19,52,95,105],"estimation":[2,20,45],"of":[3,21,54,61,76,107],"what":[4],"sound":[5,25,43],"sources":[6,26],"are,":[7],"when":[8],"they":[9,14],"occur,":[10],"and":[11,58,100,102,123,140],"from":[12,48],"where":[13],"originate":[15],"has":[16,28],"been":[17,29],"well-studied,":[18],"how":[22],"loud":[23],"these":[24],"are":[27],"often":[30],"overlooked.":[31],"Current":[32],"solutions":[33],"to":[34,40,51,63,81,93,103,118,128],"this":[35],"task,":[36],"which":[37,86],"we":[38,87],"refer":[39],"as":[41],"source-specific":[42],"level":[44],"(SSSLE),":[46],"suffer":[47],"challenges":[49],"due":[50],"impracticality":[53],"acquiring":[55],"realistic":[56,64],"data":[57],"a":[59,74],"lack":[60],"robustness":[62],"recording":[65,139],"conditions.":[66],"Recently":[67],"proposed":[68],"weakly":[69],"supervised":[70],"source":[71,79,83,98,120],"separation":[72,84,99,121],"offer":[73],"means":[75],"leveraging":[77],"clip-level":[78],"annotations":[80],"train":[82],"models,":[85],"augment":[88],"with":[89],"modified":[90],"loss":[91],"functions":[92],"bridge":[94],"gap":[96],"between":[97],"SSSLE":[101,115,136],"address":[104],"presence":[106],"background.":[108],"We":[109],"show":[110],"that":[111,135],"our":[112,130],"approach":[113],"improves":[114],"performance":[116],"compared":[117],"baseline":[119],"models":[122],"provide":[124],"an":[125],"ablation":[126],"analysis":[127],"explore":[129],"method's":[131],"design":[132],"choices,":[133],"showing":[134],"in":[137],"practical":[138],"annotation":[141],"scenarios":[142],"is":[143],"possible.":[144]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}