{"id":"https://openalex.org/W1979284044","doi":"https://doi.org/10.1109/isspit.2013.6781903","title":"Speaker localization in conferencing systems employing phase features and wavelet transform","display_name":"Speaker localization in conferencing systems employing phase features and wavelet transform","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W1979284044","doi":"https://doi.org/10.1109/isspit.2013.6781903","mag":"1979284044"},"language":"en","primary_location":{"id":"doi:10.1109/isspit.2013.6781903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspit.2013.6781903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Symposium on Signal Processing and Information Technology","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/A5056823707","display_name":"Rafa\u0142 Samborski","orcid":null},"institutions":[{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Rafal Samborski","raw_affiliation_strings":["Faculty of Computer Science, Electronics and Telecommunications, AGH University of Science and Technology, Krak\u00f3w, Poland","Dept. of Electron., AGH Univ. of Sci. & Technol., Krakow, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Electronics and Telecommunications, AGH University of Science and Technology, Krak\u00f3w, Poland","institution_ids":["https://openalex.org/I686019"]},{"raw_affiliation_string":"Dept. of Electron., AGH Univ. of Sci. & Technol., Krakow, Poland","institution_ids":["https://openalex.org/I686019"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084502401","display_name":"Mariusz Zi\u00f3\u0142ko","orcid":"https://orcid.org/0000-0001-6260-7850"},"institutions":[{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Mariusz Ziolko","raw_affiliation_strings":["Dept. of Electron., AGH Univ. of Sci. & Technol., Krakow, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electron., AGH Univ. of Sci. & Technol., Krakow, Poland","institution_ids":["https://openalex.org/I686019"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.05779446,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"134","issue":null,"first_page":"000333","last_page":"000337"},"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":0.9966999888420105,"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/T11309","display_name":"Music and Audio Processing","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6859372854232788},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6785200238227844},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6631737947463989},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6272863149642944},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6160839796066284},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5750129222869873},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5291918516159058},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.5128458142280579},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.5021486282348633},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.49392586946487427},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.46846482157707214},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.45043376088142395},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.42328527569770813},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3868069052696228},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36055833101272583},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20915278792381287},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1527080535888672},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07264918088912964}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6859372854232788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6785200238227844},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6631737947463989},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6272863149642944},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6160839796066284},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5750129222869873},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5291918516159058},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.5128458142280579},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.5021486282348633},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49392586946487427},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.46846482157707214},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.45043376088142395},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.42328527569770813},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3868069052696228},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36055833101272583},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20915278792381287},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1527080535888672},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07264918088912964},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical 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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isspit.2013.6781903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspit.2013.6781903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Symposium on Signal Processing and Information Technology","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":18,"referenced_works":["https://openalex.org/W203145905","https://openalex.org/W1555217905","https://openalex.org/W1999200217","https://openalex.org/W2014857913","https://openalex.org/W2021092941","https://openalex.org/W2045634261","https://openalex.org/W2062024414","https://openalex.org/W2113386290","https://openalex.org/W2132056833","https://openalex.org/W2140672401","https://openalex.org/W2144027068","https://openalex.org/W2148752651","https://openalex.org/W2150332440","https://openalex.org/W2159591770","https://openalex.org/W2184680890","https://openalex.org/W2491289633","https://openalex.org/W4214887259","https://openalex.org/W4255272544"],"related_works":["https://openalex.org/W2896203542","https://openalex.org/W201299990","https://openalex.org/W876328409","https://openalex.org/W4319068615","https://openalex.org/W1879255185","https://openalex.org/W2148473678","https://openalex.org/W1977167953","https://openalex.org/W3004719695","https://openalex.org/W2120442551","https://openalex.org/W2769861442"],"abstract_inverted_index":{"Some":[0],"of":[1,11,31,57,73,111,147],"existing":[2],"conference":[3],"system":[4,91,138],"employ":[5],"a":[6,86],"distant":[7],"microphone":[8,122],"array":[9,123],"instead":[10],"microphones":[12],"dedicated":[13],"for":[14],"each":[15],"user.":[16],"This":[17],"approach":[18],"is":[19,35,45,62,92,99,104,151,177,186],"much":[20,26,152],"more":[21,153],"convenient":[22],"although":[23],"suffers":[24],"from":[25],"higher":[27],"noise":[28,179],"sensitivity.":[29],"One":[30],"the":[32,42,48,55,67,79,102,135,156,182],"possible":[33],"solutions":[34],"employing":[36,127],"beamforming":[37],"techniques":[38],"to":[39],"focus":[40],"on":[41,108,118,159],"user":[43,98],"that":[44,175],"speaking":[46,100],"at":[47,101],"moment.":[49],"However,":[50],"beamformer":[51],"needs":[52],"information":[53],"about":[54,96],"direction":[56],"arrival":[58],"(DOA)":[59],"parameter":[60],"which":[61,97,139],"usually":[63],"provided":[64],"by":[65],"analysing":[66],"phase":[68,131],"differences":[69],"between":[70,184],"signals.":[71],"Effectiveness":[72],"such":[74],"solution":[75,150],"decrease":[76],"dramatically":[77],"when":[78],"environment":[80],"becomes":[81],"noisy.":[82],"In":[83],"this":[84],"paper,":[85],"novel,":[87],"robust":[88,154],"meetings":[89,169],"diarization":[90],"described.":[93],"The":[94,121,166],"decision":[95],"moment":[103],"based":[105],"not":[106],"only":[107],"spacial":[109],"features":[110,146],"signal":[112],"(i.e.,":[113],"speaker's":[114],"localization)":[115],"but":[116],"also":[117],"spectral":[119,145],"features.":[120],"estimates":[124],"speaker":[125,136,160,163],"localization":[126,164],"generalized":[128],"cross-correlation":[129],"with":[130],"transform":[132,142],"(GCC-PHAT).":[133],"Additionally,":[134],"recognition":[137,161],"employs":[140],"wavelet-Fourier":[141],"(WFT)":[143],"extracts":[144],"voice.":[148],"Described":[149],"than":[155],"one":[157],"basing":[158],"or":[162],"only.":[165],"experiments":[167],"during":[168],"in":[170],"regular":[171],"meeting":[172],"room":[173],"show":[174],"it":[176],"less":[178],"sensitive":[180],"and":[181],"switching":[183],"speakers":[185],"several":[187],"times":[188],"faster.":[189]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
