{"id":"https://openalex.org/W2398792306","doi":"https://doi.org/10.21437/interspeech.2014-217","title":"Blind speech source localization, counting and separation for 2-channel convolutive mixtures in a reverberant environment","display_name":"Blind speech source localization, counting and separation for 2-channel convolutive mixtures in a reverberant environment","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2398792306","doi":"https://doi.org/10.21437/interspeech.2014-217","mag":"2398792306"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-217","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/A5026428383","display_name":"Sayeh Mirzaei","orcid":"https://orcid.org/0000-0003-1174-2280"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sayeh Mirzaei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087514947","display_name":"Hugo Van hamme","orcid":"https://orcid.org/0000-0003-1331-5186"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hugo Van\u00a0hamme","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5074995295","display_name":"Yaser Norouzi","orcid":"https://orcid.org/0000-0002-9501-889X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaser Norouzi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.28304749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"860","last_page":"864"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9990000128746033,"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":0.9911999702453613,"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/blind-signal-separation","display_name":"Blind signal separation","score":0.7937870621681213},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6614478826522827},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6328237056732178},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6022562384605408},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5724728107452393},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5443839430809021},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5197660326957703},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.31055083870887756},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1253088414669037},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09944730997085571}],"concepts":[{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.7937870621681213},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6614478826522827},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6328237056732178},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6022562384605408},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5724728107452393},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5443839430809021},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5197660326957703},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.31055083870887756},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1253088414669037},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09944730997085571},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2014-217","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/457486","is_oa":false,"landing_page_url":"https://lirias.kuleuven.be/bitstream/123456789/457486/2/3771_final.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Annual conference of the International Speech Communication Association (ISCA) - Interspeech 2014, Singapore, 14-18 September 2014","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W210719916","https://openalex.org/W1581278537","https://openalex.org/W2066218102","https://openalex.org/W2095651369","https://openalex.org/W2096855653","https://openalex.org/W2113990625","https://openalex.org/W2121186327","https://openalex.org/W2149693148","https://openalex.org/W2156488408","https://openalex.org/W2160683204"],"related_works":["https://openalex.org/W1509813908","https://openalex.org/W2031820693","https://openalex.org/W2137168560","https://openalex.org/W1910172735","https://openalex.org/W2118307209","https://openalex.org/W2113403277","https://openalex.org/W2137288760","https://openalex.org/W2539388437","https://openalex.org/W1505387341","https://openalex.org/W2107364365"],"abstract_inverted_index":{"Copyright":[0],"\u00a9":[1],"2014":[2],"ISCA.":[3],"In":[4,31],"this":[5],"paper,":[6],"the":[7,32,35,52,65,76,117],"tasks":[8],"of":[9,24,37,39],"speech":[10,131],"source":[11,13,16,41,86,122],"localization,":[12],"counting":[14],"and":[15,136],"separation":[17,101,123],"are":[18,43,127],"addressed":[19],"for":[20,74,120],"an":[21,72],"unknown":[22],"number":[23],"sources":[25,77],"in":[26,87,133],"a":[27,46,96,106],"stereo":[28],"recording":[29],"scenario.":[30],"first":[33],"stage,":[34],"angles":[36],"arrival":[38],"individual":[40],"signals":[42],"estimated":[44],"through":[45,93],"peak":[47],"finding":[48],"scheme":[49],"applied":[50],"to":[51],"angular":[53],"spectrum":[54],"which":[55],"has":[56],"been":[57],"derived":[58],"using":[59],"non-linear":[60],"GCC-PHAT.":[61],"Then,":[62],"based":[63,78],"on":[64,79,129],"known":[66],"channel":[67],"mixture":[68],"coefficients,":[69],"we":[70],"propose":[71],"approach":[73],"separating":[75],"Maximum":[80],"Likelihood":[81],"(ML)":[82],"estimation.":[83],"The":[84,100,111,125],"predominant":[85],"each":[88],"time-frequency":[89,108],"bin":[90],"is":[91,103,113],"identified":[92],"ML":[94],"assuming":[95],"diffuse":[97],"noise":[98],"model.":[99],"performance":[102,112],"improved":[104],"over":[105],"binary":[107],"masking":[109],"method.":[110],"measured":[114],"by":[115],"obtaining":[116],"existing":[118],"metrics":[119],"blind":[121],"evaluation.":[124],"experiments":[126],"performed":[128],"synthetic":[130],"mixtures":[132],"both":[134],"anechoic":[135],"reverberant":[137],"environments.":[138]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}