{"id":"https://openalex.org/W2871284238","doi":"https://doi.org/10.1109/taslp.2018.2854871","title":"Reverberation-Robust Localization of Speakers Using Distinct Speech Onsets and Multichannel Cross Correlations","display_name":"Reverberation-Robust Localization of Speakers Using Distinct Speech Onsets and Multichannel Cross Correlations","publication_year":2018,"publication_date":"2018-07-11","ids":{"openalex":"https://openalex.org/W2871284238","doi":"https://doi.org/10.1109/taslp.2018.2854871","mag":"2871284238"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2854871","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2854871","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2604.01524","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083582801","display_name":"Shoufeng Lin","orcid":"https://orcid.org/0000-0002-9508-0706"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shoufeng Lin","raw_affiliation_strings":["Curtin University, Perth, WA, AU"],"affiliations":[{"raw_affiliation_string":"Curtin University, Perth, WA, AU","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5083582801"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1553,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88423517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"26","issue":"11","first_page":"2098","last_page":"2111"},"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":0.998199999332428,"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":0.9979000091552734,"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/reverberation","display_name":"Reverberation","score":0.9319534301757812},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7256450057029724},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6753716468811035},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6307955384254456},{"id":"https://openalex.org/keywords/cross-correlation","display_name":"Cross-correlation","score":0.6084563732147217},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5488229990005493},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.4674445390701294},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.45734238624572754},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.4228697717189789},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4203653335571289},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4185769259929657},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24274146556854248},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12244385480880737},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10863694548606873},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0694291889667511}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.9319534301757812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7256450057029724},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6753716468811035},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6307955384254456},{"id":"https://openalex.org/C163018871","wikidata":"https://www.wikidata.org/wiki/Q1302587","display_name":"Cross-correlation","level":2,"score":0.6084563732147217},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5488229990005493},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.4674445390701294},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.45734238624572754},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.4228697717189789},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4203653335571289},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4185769259929657},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24274146556854248},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12244385480880737},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10863694548606873},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0694291889667511},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2018.2854871","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2854871","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:arXiv.org:2604.01524","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2604.01524","pdf_url":"https://arxiv.org/pdf/2604.01524","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2604.01524","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2604.01524","pdf_url":"https://arxiv.org/pdf/2604.01524","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2871284238.pdf","grobid_xml":"https://content.openalex.org/works/W2871284238.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1493163583","https://openalex.org/W1557595030","https://openalex.org/W1946152311","https://openalex.org/W1964538581","https://openalex.org/W1987906574","https://openalex.org/W1993678034","https://openalex.org/W1998428434","https://openalex.org/W2023254078","https://openalex.org/W2025127228","https://openalex.org/W2037182618","https://openalex.org/W2043694038","https://openalex.org/W2046317813","https://openalex.org/W2060364934","https://openalex.org/W2061074721","https://openalex.org/W2067584370","https://openalex.org/W2069447433","https://openalex.org/W2075076415","https://openalex.org/W2083145261","https://openalex.org/W2086286498","https://openalex.org/W2092818693","https://openalex.org/W2113638573","https://openalex.org/W2114537326","https://openalex.org/W2117029426","https://openalex.org/W2123422215","https://openalex.org/W2126885789","https://openalex.org/W2128131274","https://openalex.org/W2128970593","https://openalex.org/W2135080377","https://openalex.org/W2135817141","https://openalex.org/W2136172079","https://openalex.org/W2141904749","https://openalex.org/W2149095746","https://openalex.org/W2151938450","https://openalex.org/W2154604839","https://openalex.org/W2169073093","https://openalex.org/W2170393302","https://openalex.org/W2171834532","https://openalex.org/W2172006521","https://openalex.org/W2315268655","https://openalex.org/W2523573275","https://openalex.org/W2561557072","https://openalex.org/W2765170997","https://openalex.org/W2898344085","https://openalex.org/W2963846200","https://openalex.org/W3127686677","https://openalex.org/W6633511732","https://openalex.org/W6744857890","https://openalex.org/W6789826613","https://openalex.org/W7027820433"],"related_works":["https://openalex.org/W1491017269","https://openalex.org/W2043736742","https://openalex.org/W2517234899","https://openalex.org/W2054208617","https://openalex.org/W3108996945","https://openalex.org/W2136599659","https://openalex.org/W1749143132","https://openalex.org/W2130361043","https://openalex.org/W2769113897","https://openalex.org/W2871284238"],"abstract_inverted_index":{"Many":[0],"speaker":[1,11],"localization":[2,12,170],"methods":[3,128,178],"can":[4,179],"be":[5],"found":[6],"in":[7,21,90,154,186],"the":[8,22,44,70,82,100,108,123,176],"literature.":[9],"However,":[10],"under":[13,132],"strong":[14],"reverberation":[15,124],"still":[16],"remains":[17],"a":[18,62,155],"major":[19],"challenge":[20],"real-world":[23],"applications.":[24],"This":[25],"paper":[26],"proposes":[27],"two":[28],"algorithms":[29],"for":[30],"localizing":[31],"speakers":[32],"using":[33,115,135],"microphone":[34,48],"array":[35],"recordings":[36,153],"of":[37,86,102,118,146,188],"reverberated":[38],"sounds.":[39],"To":[40,57],"separate":[41],"concurrent":[42],"speakers,":[43,185],"first":[45],"algorithm":[46,106],"decomposes":[47],"signals":[49,139],"spectro-temporally":[50],"into":[51],"subbands":[52],"via":[53],"an":[54],"auditory":[55],"filterbank.":[56],"suppress":[58],"reverberation,":[59],"we":[60],"propose":[61,79],"novel":[63],"speech":[64,71,88],"onset":[65],"detection":[66],"approach":[67],"derived":[68],"from":[69],"signal":[72],"and":[73,77,183],"impulse":[74],"response":[75],"models,":[76],"further":[78],"to":[80,98,121,148],"formulate":[81],"multichannel":[83],"cross-correlation":[84,110],"coefficient":[85],"encoded":[87],"onsets":[89],"each":[91],"subband.":[92],"The":[93,104,126],"subband":[94],"results":[95,173],"are":[96],"combined":[97],"estimate":[99],"directions-of-arrival":[101],"speakers.":[103],"second":[105],"extends":[107],"generalized":[109],"phase":[111],"transform":[112],"method":[113],"by":[114],"redundant":[116],"information":[117],"multiple":[119],"microphones":[120],"address":[122],"problem.":[125],"proposed":[127,177],"have":[129],"been":[130],"evaluated":[131],"adverse":[133],"conditions":[134],"not":[136],"only":[137],"simulated":[138],"(reverberation":[140],"time":[141],"T":[142],"<sub":[143,160],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[144,161],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">60</sub>":[145,162],"up":[147],"1":[149],"s)":[150],"but":[151],"also":[152],"real":[156],"reverberant":[157],"room":[158],"(T":[159],"\u2248":[163],"0.65":[164],"s).":[165],"Comparing":[166],"with":[167],"some":[168],"state-of-the-art":[169],"methods,":[171],"experimental":[172],"confirm":[174],"that":[175],"reliably":[180],"locate":[181],"static":[182],"moving":[184],"presence":[187],"reverberation.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4}],"updated_date":"2026-04-06T07:47:59.780226","created_date":"2025-10-10T00:00:00"}
