{"id":"https://openalex.org/W3142280584","doi":"https://doi.org/10.1186/s13636-021-00201-y","title":"NMF-weighted SRP for multi-speaker direction of arrival estimation: robustness to spatial aliasing while exploiting sparsity in the atom-time domain","display_name":"NMF-weighted SRP for multi-speaker direction of arrival estimation: robustness to spatial aliasing while exploiting sparsity in the atom-time domain","publication_year":2021,"publication_date":"2021-03-03","ids":{"openalex":"https://openalex.org/W3142280584","doi":"https://doi.org/10.1186/s13636-021-00201-y","mag":"3142280584"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-021-00201-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00201-y","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00201-y","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00201-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031663384","display_name":"Sushmita Thakallapalli","orcid":"https://orcid.org/0000-0002-1742-5668"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sushmita Thakallapalli","raw_affiliation_strings":["Speech Processing Laboratory, International Institute of Information Technology, Hyderabad, India"],"raw_orcid":"https://orcid.org/0000-0002-1742-5668","affiliations":[{"raw_affiliation_string":"Speech Processing Laboratory, International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058673990","display_name":"Suryakanth V. Gangashetty","orcid":"https://orcid.org/0000-0001-6745-4363"},"institutions":[{"id":"https://openalex.org/I4210126787","display_name":"Andhra Pradesh Forest Department","ror":"https://ror.org/02xr5ws27","country_code":"IN","type":"government","lineage":["https://openalex.org/I2800401362","https://openalex.org/I4210126787"]},{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Suryakanth V. Gangashetty","raw_affiliation_strings":["Present address: K L University, Guntur, Andhra Pradesh, India","Speech Processing Laboratory, International Institute of Information Technology, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Present address: K L University, Guntur, Andhra Pradesh, India","institution_ids":["https://openalex.org/I4210126787"]},{"raw_affiliation_string":"Speech Processing Laboratory, International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081844255","display_name":"Nilesh Madhu","orcid":"https://orcid.org/0000-0001-9131-3309"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Nilesh Madhu","raw_affiliation_strings":["IDLab, Dept. Electronics & Information Systems, Ghent University - imec, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDLab, Dept. Electronics & Information Systems, Ghent University - imec, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031663384"],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":0.8377,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71051207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"2021","issue":"1","first_page":null,"last_page":null},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/narrowband","display_name":"Narrowband","score":0.7249581217765808},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6955476999282837},{"id":"https://openalex.org/keywords/broadband","display_name":"Broadband","score":0.5440711975097656},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5258339643478394},{"id":"https://openalex.org/keywords/aliasing","display_name":"Aliasing","score":0.47399961948394775},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4678277373313904},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.4582606256008148},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4515000879764557},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.41911476850509644},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4176592528820038},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40504854917526245},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36032527685165405},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.35502487421035767},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27201396226882935},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2564682960510254},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1576966941356659},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1547645628452301},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10782194137573242}],"concepts":[{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.7249581217765808},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6955476999282837},{"id":"https://openalex.org/C509933004","wikidata":"https://www.wikidata.org/wiki/Q194163","display_name":"Broadband","level":2,"score":0.5440711975097656},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5258339643478394},{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.47399961948394775},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4678277373313904},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.4582606256008148},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4515000879764557},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.41911476850509644},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4176592528820038},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40504854917526245},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36032527685165405},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.35502487421035767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27201396226882935},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2564682960510254},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1576966941356659},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1547645628452301},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10782194137573242},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"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/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s13636-021-00201-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00201-y","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00201-y","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:archive.ugent.be:8700074","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-8700074","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 1687-4722","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:a1c26c4906c6421ca287c04871f913bd","is_oa":true,"landing_page_url":"https://doaj.org/article/a1c26c4906c6421ca287c04871f913bd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2021, Iss 1, Pp 1-18 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-021-00201-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00201-y","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00201-y","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3142280584.pdf","grobid_xml":"https://content.openalex.org/works/W3142280584.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W126779258","https://openalex.org/W274496805","https://openalex.org/W1515932869","https://openalex.org/W1549884461","https://openalex.org/W1555217905","https://openalex.org/W1570694229","https://openalex.org/W1969977143","https://openalex.org/W1976391658","https://openalex.org/W2001372085","https://openalex.org/W2004140730","https://openalex.org/W2016891207","https://openalex.org/W2018731188","https://openalex.org/W2046317813","https://openalex.org/W2052897490","https://openalex.org/W2068068201","https://openalex.org/W2073006643","https://openalex.org/W2096439661","https://openalex.org/W2100335648","https://openalex.org/W2100818340","https://openalex.org/W2104422351","https://openalex.org/W2128970593","https://openalex.org/W2137867936","https://openalex.org/W2138456300","https://openalex.org/W2144584285","https://openalex.org/W2148886336","https://openalex.org/W2150384167","https://openalex.org/W2153579005","https://openalex.org/W2163085538","https://openalex.org/W2168744649","https://openalex.org/W2175634487","https://openalex.org/W2502139158","https://openalex.org/W2533459608","https://openalex.org/W2575498233","https://openalex.org/W2612685246","https://openalex.org/W2783473931","https://openalex.org/W2888793942","https://openalex.org/W2897977894","https://openalex.org/W2916583660","https://openalex.org/W2916721784","https://openalex.org/W2998572311","https://openalex.org/W3139695047","https://openalex.org/W3143596294","https://openalex.org/W6600168311","https://openalex.org/W6600503824","https://openalex.org/W6602518823","https://openalex.org/W6611060287","https://openalex.org/W6643149233","https://openalex.org/W6825584742"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W2146544734"],"abstract_inverted_index":{"Abstract":[0],"Localization":[1],"of":[2,16,27,118,150,172,183,201,235,243],"multiple":[3,134],"speakers":[4],"using":[5,145],"microphone":[6],"arrays":[7,79,99],"remains":[8],"a":[9,111,115,162,173,198],"challenging":[10],"problem,":[11],"especially":[12],"in":[13,29,53,128,143,241],"the":[14,25,36,54,69,87,129,151,156,181,184,193,227,231],"presence":[15],"noise":[17],"and":[18,51,123,155,186,189,216,218,237,247],"reverberation.":[19],"State-of-the-art":[20],"localization":[21,76,157,195,239,248],"algorithms":[22],"generally":[23],"exploit":[24,39,49,68],"sparsity":[26,41,50,127],"speech":[28],"some":[30],"representation":[31,131],"for":[32,42,78,98,132,168,197],"this":[33],"purpose.":[34],"Whereas":[35],"broadband":[37,119,163,187,238],"approaches":[38,46,58,188,240],"time-domain":[40],"multi-speaker":[43,194],"localization,":[44],"narrowband":[45,185,236],"can":[47],"additionally":[48],"disjointness":[52],"time-frequency":[55],"representation.":[56],"Broadband":[57],"are":[59,90],"robust":[60],"to":[61,74,92],"spatial":[62,93],"aliasing":[63],"but":[64],"do":[65],"not":[66],"optimally":[67],"frequency":[70],"domain":[71],"sparsity,":[72],"leading":[73],"poor":[75],"performance":[77],"with":[80,100],"short":[81],"inter-microphone":[82,102,202],"distances.":[83],"Narrowband":[84],"approaches,":[85],"on":[86,192,207,219],"other":[88],"hand,":[89],"vulnerable":[91],"aliasing,":[94],"making":[95],"them":[96],"unsuitable":[97],"large":[101],"spacing.":[103],"Proposed":[104],"here":[105],"is":[106,141,159],"an":[107],"approach":[108,167,178,229],"that":[109],"decomposes":[110],"signal":[112,126],"spectrum":[113],"into":[114,139],"weighted":[116],"sum":[117],"spectral":[120],"components":[121],"(atoms)":[122],"then":[124],"exploits":[125],"time-atom":[130],"simultaneous":[133],"source":[135,244],"localization.":[136],"The":[137],"decomposition":[138],"atoms":[140],"performed":[142],"situ":[144],"non-negative":[146],"matrix":[147],"factorization":[148],"(NMF)":[149],"short-term":[152],"amplitude":[153],"spectra":[154],"estimate":[158],"obtained":[160],"via":[161],"steered-response":[164],"power":[165],"(SRP)":[166],"each":[169],"active":[170],"atom":[171],"time":[174],"frame.":[175],"This":[176],"SRP-NMF":[177,228],"thereby":[179],"combines":[180],"advantages":[182],"performs":[190],"well":[191],"task":[196],"broad":[199],"range":[200],"spacings.":[203],"On":[204],"tests":[205],"conducted":[206],"real-world":[208],"data":[209,220],"from":[210,222],"public":[211],"challenges":[212],"such":[213],"as":[214],"SiSEC":[215],"LOCATA,":[217],"generated":[221],"recorded":[223],"room":[224],"impulse":[225],"responses,":[226],"outperforms":[230],"commonly":[232],"used":[233],"variants":[234],"terms":[242],"detection":[245],"capability":[246],"accuracy.":[249]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}