{"id":"https://openalex.org/W3132182240","doi":"https://doi.org/10.1109/taslp.2021.3060257","title":"Neural Network Adaptation and Data Augmentation for Multi-Speaker Direction-of-Arrival Estimation","display_name":"Neural Network Adaptation and Data Augmentation for Multi-Speaker Direction-of-Arrival Estimation","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3132182240","doi":"https://doi.org/10.1109/taslp.2021.3060257","mag":"3132182240"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3060257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3060257","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/284980","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103162780","display_name":"Weipeng He","orcid":"https://orcid.org/0000-0002-3874-3083"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Weipeng He","raw_affiliation_strings":["EPFL, Lausanne, Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076409146","display_name":"Petr Motl\u00ed\u010dek","orcid":"https://orcid.org/0000-0001-6467-1119"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Petr Motlicek","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053358969","display_name":"Jean\u2010Marc Odobez","orcid":"https://orcid.org/0000-0002-9537-9898"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jean-Marc Odobez","raw_affiliation_strings":["EPFL, Lausanne, Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103162780"],"corresponding_institution_ids":["https://openalex.org/I5124864","https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":5.3327,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.9647735,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"1303","last_page":"1317"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11309","display_name":"Music and Audio Processing","score":0.9965000152587891,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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":0.811499834060669},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5751184821128845},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5620598196983337},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5514230132102966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5210204124450684},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.5013959407806396},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4997236728668213},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47547927498817444},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4746307134628296},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.4647625684738159},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4472252428531647},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4222852289676666},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40192437171936035},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.396003395318985},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3319791555404663},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07030099630355835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.811499834060669},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5751184821128845},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5620598196983337},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5514230132102966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5210204124450684},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.5013959407806396},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4997236728668213},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47547927498817444},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4746307134628296},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4647625684738159},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4472252428531647},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4222852289676666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40192437171936035},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.396003395318985},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3319791555404663},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07030099630355835},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"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/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2021.3060257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3060257","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:infoscience.epfl.ch:284980","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/284980","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"research article"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:284980","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/284980","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"research article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1422086691","https://openalex.org/W1522301498","https://openalex.org/W1554587488","https://openalex.org/W1569447338","https://openalex.org/W1593557000","https://openalex.org/W1603075283","https://openalex.org/W1882958252","https://openalex.org/W1969110495","https://openalex.org/W1971635570","https://openalex.org/W2026573146","https://openalex.org/W2035083192","https://openalex.org/W2037949455","https://openalex.org/W2046317813","https://openalex.org/W2078528333","https://openalex.org/W2084637638","https://openalex.org/W2090024980","https://openalex.org/W2104094955","https://openalex.org/W2108668360","https://openalex.org/W2112483442","https://openalex.org/W2113638573","https://openalex.org/W2114863372","https://openalex.org/W2117678320","https://openalex.org/W2122796820","https://openalex.org/W2166682639","https://openalex.org/W2194775991","https://openalex.org/W2403149086","https://openalex.org/W2405404760","https://openalex.org/W2519758402","https://openalex.org/W2559085405","https://openalex.org/W2586642235","https://openalex.org/W2592109325","https://openalex.org/W2593116425","https://openalex.org/W2663904211","https://openalex.org/W2765962757","https://openalex.org/W2772736377","https://openalex.org/W2810934215","https://openalex.org/W2883288608","https://openalex.org/W2885219692","https://openalex.org/W2888793942","https://openalex.org/W2888842465","https://openalex.org/W2891627435","https://openalex.org/W2937324313","https://openalex.org/W2940285530","https://openalex.org/W2963275094","https://openalex.org/W2963339453","https://openalex.org/W2963826681","https://openalex.org/W2964342924","https://openalex.org/W2966743431","https://openalex.org/W2968054085","https://openalex.org/W3021380725","https://openalex.org/W3081461453","https://openalex.org/W3100871498","https://openalex.org/W3105684258","https://openalex.org/W3149173221","https://openalex.org/W4213425930","https://openalex.org/W4233648669","https://openalex.org/W6628353819","https://openalex.org/W6631190155","https://openalex.org/W6633847657","https://openalex.org/W6639480849","https://openalex.org/W6676840641","https://openalex.org/W6685415078","https://openalex.org/W6713369370","https://openalex.org/W6766648584"],"related_works":["https://openalex.org/W4376166954","https://openalex.org/W2152148513","https://openalex.org/W4281397339","https://openalex.org/W2161947961","https://openalex.org/W4312910505","https://openalex.org/W2783380393","https://openalex.org/W2116623987","https://openalex.org/W2280198878","https://openalex.org/W2951876757","https://openalex.org/W2900122540"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"have":[3],"been":[4],"successfully":[5],"applied":[6,89,153],"to":[7,30,90,154],"sound":[8,68],"direction-of-arrival":[9,43],"estimation":[10,44,151],"under":[11],"challenging":[12],"conditions.":[13],"However,":[14],"such":[15],"a":[16,20,38,99],"learning-based":[17],"approach":[18,40,130],"requires":[19],"large":[21],"amount":[22],"of":[23,67,157],"labeled":[24],"training":[25],"data,":[26],"which":[27,106],"is":[28,88],"difficult":[29],"acquire.":[31],"To":[32],"address":[33],"this":[34],"problem,":[35],"we":[36],"propose":[37],"novel":[39],"for":[41,102,149],"multi-speaker":[42],"with":[45,57,64,121,160],"data":[46,56,62,76,125,139,162],"augmentation":[47],"and":[48,59,111],"weakly-supervised":[49,85],"domain":[50,55,86],"adaptation.":[51],"We":[52,97],"generate":[53],"source":[54],"simulation,":[58],"collect":[60],"real":[61,75,122,138],"annotated":[63],"the":[65,71,94,103,108,112,117,136],"number":[66],"sources":[69],"as":[70,134],"weak":[72,109],"labels.":[73],"The":[74],"are":[77,140],"further":[78],"augmented":[79,118],"by":[80],"mixing":[81],"single-source":[82],"segments.":[83],"Then,":[84],"adaptation":[87,104],"models":[91,152],"pre-trained":[92],"on":[93],"simulated":[95],"data.":[96,119],"define":[98],"loss":[100],"function":[101],"process":[105],"exploits":[107],"labels":[110],"mixture":[113],"component":[114],"information":[115],"in":[116],"Experiments":[120],"robot":[123],"audio":[124],"show":[126],"that":[127],"our":[128],"proposed":[129],"achieves":[131],"similar":[132],"performance":[133],"if":[135],"fully-labeled":[137],"used.":[141],"This":[142],"paper":[143],"suggests":[144],"an":[145],"effective":[146],"development":[147],"procedure":[148],"DOA":[150],"new":[155],"types":[156],"microphone":[158],"arrays":[159],"minimal":[161],"collection":[163],"efforts.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}