{"id":"https://openalex.org/W4372348953","doi":"https://doi.org/10.1109/icassp49357.2023.10094573","title":"Real-Time Target Sound Extraction","display_name":"Real-Time Target Sound Extraction","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372348953","doi":"https://doi.org/10.1109/icassp49357.2023.10094573"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5080881573","display_name":"Bandhav Veluri","orcid":"https://orcid.org/0000-0002-5086-9092"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bandhav Veluri","raw_affiliation_strings":["University of Washington,Paul G. Allen School of Computer Science & Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,Paul G. Allen School of Computer Science & Engineering,USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062650938","display_name":"Justin Chan","orcid":"https://orcid.org/0000-0002-1471-6187"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Chan","raw_affiliation_strings":["University of Washington,Paul G. Allen School of Computer Science & Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,Paul G. Allen School of Computer Science & Engineering,USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035670633","display_name":"Malek Itani","orcid":"https://orcid.org/0009-0002-7249-2641"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Malek Itani","raw_affiliation_strings":["University of Washington,Paul G. Allen School of Computer Science & Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,Paul G. Allen School of Computer Science & Engineering,USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091414943","display_name":"Tuochao Chen","orcid":"https://orcid.org/0000-0002-8031-5066"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tuochao Chen","raw_affiliation_strings":["University of Washington,Paul G. Allen School of Computer Science & Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,Paul G. Allen School of Computer Science & Engineering,USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011077730","display_name":"Shyamnath Gollakota","orcid":"https://orcid.org/0000-0002-9863-3054"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shyamnath Gollakota","raw_affiliation_strings":["University of Washington,Paul G. Allen School of Computer Science & Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,Paul G. Allen School of Computer Science & Engineering,USA","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.0209,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.97975734,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"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":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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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":0.8143653869628906},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6806543469429016},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6037141680717468},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4908188283443451},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.47585317492485046},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4643196761608124},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44898679852485657},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4346710443496704},{"id":"https://openalex.org/keywords/digital-subscriber-line","display_name":"Digital subscriber line","score":0.41100722551345825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3630620539188385},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3540462851524353},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.32724615931510925},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28299182653427124},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08312112092971802}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143653869628906},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6806543469429016},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6037141680717468},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4908188283443451},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.47585317492485046},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4643196761608124},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44898679852485657},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4346710443496704},{"id":"https://openalex.org/C201374245","wikidata":"https://www.wikidata.org/wiki/Q104534","display_name":"Digital subscriber line","level":2,"score":0.41100722551345825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3630620539188385},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3540462851524353},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.32724615931510925},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28299182653427124},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08312112092971802},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":49,"referenced_works":["https://openalex.org/W2031647436","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2519091744","https://openalex.org/W2593116425","https://openalex.org/W2610428556","https://openalex.org/W2771361008","https://openalex.org/W2884535146","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2963189033","https://openalex.org/W2964058413","https://openalex.org/W2973062255","https://openalex.org/W2981816492","https://openalex.org/W2988200020","https://openalex.org/W2989581421","https://openalex.org/W2998657200","https://openalex.org/W3004910802","https://openalex.org/W3015199127","https://openalex.org/W3095263845","https://openalex.org/W3097777922","https://openalex.org/W3099330747","https://openalex.org/W3160972914","https://openalex.org/W3161873870","https://openalex.org/W3163652268","https://openalex.org/W3197762568","https://openalex.org/W3198543387","https://openalex.org/W3206706278","https://openalex.org/W4224871700","https://openalex.org/W4224929689","https://openalex.org/W4226151502","https://openalex.org/W4283031696","https://openalex.org/W4283320926","https://openalex.org/W4283329643","https://openalex.org/W4283727958","https://openalex.org/W4283800072","https://openalex.org/W4289665794","https://openalex.org/W4295723153","https://openalex.org/W4296069305","https://openalex.org/W4297841626","https://openalex.org/W4310873168","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6752516136","https://openalex.org/W6753583920","https://openalex.org/W6770453446","https://openalex.org/W6810500084","https://openalex.org/W6839002775","https://openalex.org/W6839547487"],"related_works":["https://openalex.org/W1622568043","https://openalex.org/W2056183469","https://openalex.org/W2055565857","https://openalex.org/W4230802329","https://openalex.org/W2151852566","https://openalex.org/W2087366038","https://openalex.org/W4299645117","https://openalex.org/W2164592990","https://openalex.org/W1498610659","https://openalex.org/W2197898492"],"abstract_inverted_index":{"We":[0,100],"present":[1],"the":[2,33,41,63,82],"first":[3],"neural":[4],"network":[5],"model":[6,93],"to":[7,81],"achieve":[8],"real-time":[9],"and":[10,35,95,104],"streaming":[11],"target":[12],"sound":[13],"extraction.":[14],"To":[15],"accomplish":[16],"this,":[17],"we":[18],"propose":[19],"Waveformer,":[20],"an":[21],"encoder-decoder":[22],"architecture":[23,45],"with":[24],"a":[25,36,56,90,96],"stack":[26],"of":[27,66],"dilated":[28,47],"causal":[29,48],"convolution":[30],"layers":[31],"as":[32,40,72,74],"encoder,":[34],"transformer":[37],"decoder":[38],"layer":[39],"decoder.":[42],"This":[43],"hybrid":[44],"uses":[46],"convolutions":[49],"for":[50,85],"processing":[51],"large":[52],"receptive":[53],"fields":[54],"in":[55,78],"computationally":[57],"efficient":[58],"manner,":[59],"while":[60,88],"also":[61],"leveraging":[62],"generalization":[64],"performance":[65],"transformer-based":[67],"architectures.":[68],"Our":[69],"evaluations":[70],"show":[71],"much":[73],"2.2\u20133.3":[75],"dB":[76],"improvement":[77],"SI-SNRi":[79],"compared":[80],"prior":[83],"models":[84],"this":[86],"task":[87],"having":[89],"1.2\u20134x":[91],"smaller":[92],"size":[94],"1.5\u20132x":[97],"lower":[98],"runtime.":[99],"provide":[101],"code,":[102],"dataset,":[103],"audio":[105],"samples:":[106],"https://waveformer.cs.washington.edu/.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}