{"id":"https://openalex.org/W2672714283","doi":"https://doi.org/10.1109/icassp.2017.7953332","title":"Speaker localization in reverberant rooms based on direct path dominance test statistics","display_name":"Speaker localization in reverberant rooms based on direct path dominance test statistics","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2672714283","doi":"https://doi.org/10.1109/icassp.2017.7953332","mag":"2672714283"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5019518606","display_name":"Boaz Rafaely","orcid":"https://orcid.org/0000-0002-6819-9250"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Boaz Rafaely","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer-Sheva, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer-Sheva, Israel","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007017640","display_name":"Dorothea Kolossa","orcid":"https://orcid.org/0000-0003-0678-3053"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dorothea Kolossa","raw_affiliation_strings":["Department of Electrical Engineering and Information Technology, Ruhr-Universit\u00e4t Bochum, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology, Ruhr-Universit\u00e4t Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3616,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.93401119,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6120","last_page":"6124"},"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/T10931","display_name":"Direction-of-Arrival Estimation Techniques","score":0.9968000054359436,"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":0.9961000084877014,"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/reverberation","display_name":"Reverberation","score":0.8493239879608154},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.6777315139770508},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5912365317344666},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5406988859176636},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.5368244051933289},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5031763911247253},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4933711588382721},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4862765073776245},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.43905481696128845},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.42479458451271057},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.41504979133605957},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3233104348182678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29648175835609436},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2821680009365082},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.17143568396568298},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12426412105560303},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.12246048450469971},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12099429965019226},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.09124353528022766}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8493239879608154},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.6777315139770508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5912365317344666},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5406988859176636},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.5368244051933289},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5031763911247253},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4933711588382721},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4862765073776245},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.43905481696128845},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.42479458451271057},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.41504979133605957},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3233104348182678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29648175835609436},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2821680009365082},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.17143568396568298},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12426412105560303},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.12246048450469971},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12099429965019226},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.09124353528022766},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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":13,"referenced_works":["https://openalex.org/W278097168","https://openalex.org/W1964998538","https://openalex.org/W1966081805","https://openalex.org/W2060108923","https://openalex.org/W2113638573","https://openalex.org/W2117678320","https://openalex.org/W2128131274","https://openalex.org/W2161495957","https://openalex.org/W2163994287","https://openalex.org/W2170393302","https://openalex.org/W2488678869","https://openalex.org/W2494085323","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W1562475690","https://openalex.org/W1488529827","https://openalex.org/W4389082013","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"],"abstract_inverted_index":{"Speaker":[0],"localization":[1,39,45,104],"using":[2],"microphone":[3],"arrays":[4],"is":[5,34,67,92,99],"typically":[6],"based":[7,68,94,110],"on":[8,69,95,111],"the":[9,21,31,52,56,62,73,76,82,119,122,129,132],"expected":[10],"phase":[11],"and":[12,38,125],"amplitude":[13],"differences":[14],"between":[15,75],"microphones":[16],"as":[17],"a":[18,43,89,106,112],"function":[19],"of":[20,61,81,121,131],"wave":[22],"arrival":[23],"direction.":[24],"However,":[25],"in":[26,55,105],"rooms":[27],"with":[28],"significant":[29],"reverberation,":[30],"direct":[32],"sound":[33],"contaminated":[35],"by":[36],"reflections":[37],"often":[40],"fails.":[41],"Recently,":[42],"reverberation-robust":[44],"method":[46,66,124],"was":[47],"proposed,":[48],"which":[49,98],"uses":[50],"only":[51],"direct-path":[53],"bins":[54],"short-time":[57],"Fourier":[58],"transform":[59],"(STFT)":[60],"speech":[63],"signals.":[64],"The":[65,116],"thresholding":[70],"according":[71],"to":[72],"ratio":[74],"first":[77],"two":[78],"singular":[79],"values":[80],"spatial":[83],"spectrum":[84],"matrix.":[85],"In":[86],"this":[87,96],"work,":[88],"confidence":[90],"measure":[91],"developed":[93],"ratio,":[97],"then":[100],"used":[101],"for":[102],"speaker":[103],"statistical":[107],"estimation":[108],"framework,":[109],"Gaussian":[113],"mixture":[114],"model.":[115],"paper":[117],"presents":[118],"theory":[120],"proposed":[123],"simulation":[126],"examples":[127],"validating":[128],"advantages":[130],"new":[133],"approach.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}