{"id":"https://openalex.org/W4375868926","doi":"https://doi.org/10.1109/icassp49357.2023.10095970","title":"Multi-Microphone Speaker Separation by Spatial Regions","display_name":"Multi-Microphone Speaker Separation by Spatial Regions","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868926","doi":"https://doi.org/10.1109/icassp49357.2023.10095970"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095970","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/A5072691285","display_name":"Julian Wechsler","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Julian Wechsler","raw_affiliation_strings":["International Audio Laboratories Erlangen,Erlangen,Germany,91058"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004929413","display_name":"Srikanth Raj Chetupalli","orcid":"https://orcid.org/0000-0002-2186-5420"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Srikanth Raj Chetupalli","raw_affiliation_strings":["International Audio Laboratories Erlangen,Erlangen,Germany,91058"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049026973","display_name":"Wolfgang Mack","orcid":"https://orcid.org/0000-0002-8489-7382"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang Mack","raw_affiliation_strings":["International Audio Laboratories Erlangen,Erlangen,Germany,91058"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031626756","display_name":"Emanu\u00ebl A. P. Habets","orcid":"https://orcid.org/0000-0002-2613-8046"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Emanu\u00ebl A. P. Habets","raw_affiliation_strings":["International Audio Laboratories Erlangen,Erlangen,Germany,91058"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072691285"],"corresponding_institution_ids":["https://openalex.org/I4210123192"],"apc_list":null,"apc_paid":null,"fwci":2.0332,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87331789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"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/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7580820322036743},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6573202013969421},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6345612406730652},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.5539966225624084},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5218431353569031},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.47178885340690613},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4299764931201935},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4206075072288513},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3884338438510895},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3835858404636383},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3731081783771515},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1192314624786377},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07906574010848999},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.07543620467185974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7580820322036743},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6573202013969421},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6345612406730652},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.5539966225624084},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5218431353569031},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.47178885340690613},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4299764931201935},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4206075072288513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3884338438510895},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3835858404636383},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3731081783771515},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1192314624786377},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07906574010848999},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.07543620467185974},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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/icassp49357.2023.10095970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095970","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1965023548","https://openalex.org/W2089946642","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2892163332","https://openalex.org/W2899515918","https://openalex.org/W2918296821","https://openalex.org/W2944972166","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W2981976899","https://openalex.org/W3027008958","https://openalex.org/W3043433769","https://openalex.org/W3092796334","https://openalex.org/W3124972797","https://openalex.org/W3132830522","https://openalex.org/W3133514748","https://openalex.org/W3151851237","https://openalex.org/W3161301466","https://openalex.org/W3205004157","https://openalex.org/W3206110053","https://openalex.org/W4285069955","https://openalex.org/W4294891356","https://openalex.org/W4297841581","https://openalex.org/W4312219134","https://openalex.org/W4312245440","https://openalex.org/W4372271367","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6762182681","https://openalex.org/W6769975201","https://openalex.org/W6777776875","https://openalex.org/W6780226713","https://openalex.org/W6784139575","https://openalex.org/W6839581590","https://openalex.org/W6842384739"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W4240587264","https://openalex.org/W2900122540","https://openalex.org/W2963983801","https://openalex.org/W3119734852","https://openalex.org/W2804363668","https://openalex.org/W1515932869","https://openalex.org/W2043735059"],"abstract_inverted_index":{"We":[0,12,51,111],"consider":[1],"the":[2,29,32,99,105,132],"task":[3],"of":[4,8,60,81,122],"region-based":[5],"source":[6,21],"separation":[7],"reverberant":[9],"multi-microphone":[10],"recordings.":[11],"assume":[13],"pre-defined":[14],"spatial":[15,34,49,68,135],"regions":[16,35,82,123],"with":[17,107],"a":[18,39,44,53,57,61,78,92,119,141],"single":[19],"active":[20],"per":[22],"region.":[23],"The":[24,72,137],"objective":[25],"is":[26,74],"to":[27,76,83,97,124],"estimate":[28],"signals":[30,47],"from":[31,88],"individual":[33],"as":[36],"captured":[37],"by":[38,144],"reference":[40],"microphone":[41],"while":[42],"retaining":[43],"correspondence":[45],"between":[46],"and":[48,69,130],"regions.":[50],"propose":[52],"data-driven":[54],"approach":[55],"using":[56],"modified":[58],"version":[59],"state-of-the-art":[62],"network,":[63],"where":[64],"different":[65],"layers":[66],"model":[67],"spectro-temporal":[70],"information.":[71,101,136],"network":[73,84,106,125,139,143],"trained":[75],"enforce":[77],"fixed":[79,120],"mapping":[80,121],"outputs.":[85],"Using":[86],"speech":[87],"LibriMix,":[89],"we":[90,103],"construct":[91],"data":[93],"set":[94],"specifically":[95],"designed":[96],"contain":[98],"region":[100],"Additionally,":[102],"train":[104],"permutation":[108],"invariant":[109],"training.":[110],"show":[112],"that":[113,131],"both":[114],"training":[115],"methods":[116],"result":[117],"in":[118,147],"outputs,":[126],"achieve":[127],"comparable":[128],"performance,":[129],"networks":[133],"exploit":[134],"proposed":[138],"outperforms":[140],"baseline":[142],"1.5":[145],"dB":[146],"scale-invariant":[148],"signal-to-distortion":[149],"ratio.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
