{"id":"https://openalex.org/W2095415261","doi":"https://doi.org/10.1109/istel.2012.6483104","title":"Binaural speech separation based on the time-frequency binary mask","display_name":"Binaural speech separation based on the time-frequency binary mask","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W2095415261","doi":"https://doi.org/10.1109/istel.2012.6483104","mag":"2095415261"},"language":"en","primary_location":{"id":"doi:10.1109/istel.2012.6483104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/istel.2012.6483104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th International Symposium on Telecommunications (IST)","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/A5110204706","display_name":"Azar Mahmoodzadeh","orcid":"https://orcid.org/0000-0002-1517-9985"},"institutions":[{"id":"https://openalex.org/I155419210","display_name":"Islamic Azad University, Science and Research Branch","ror":"https://ror.org/03187yj51","country_code":"IR","type":"education","lineage":["https://openalex.org/I110525433","https://openalex.org/I155419210"]},{"id":"https://openalex.org/I91138267","display_name":"Islamic Azad University of Shiraz","ror":"https://ror.org/03xbchh53","country_code":"IR","type":"education","lineage":["https://openalex.org/I110525433","https://openalex.org/I91138267"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"A. Mahmoodzadeh","raw_affiliation_strings":["EE Department, Islamic Azad University, Shiraz, Iran","EE Department Islamic Azad University-Fars Science and Research Branch Shiraz, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EE Department, Islamic Azad University, Shiraz, Iran","institution_ids":["https://openalex.org/I91138267"]},{"raw_affiliation_string":"EE Department Islamic Azad University-Fars Science and Research Branch Shiraz, Iran","institution_ids":["https://openalex.org/I155419210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027512330","display_name":"Hamid Reza Abutalebi","orcid":"https://orcid.org/0000-0002-1408-5637"},"institutions":[{"id":"https://openalex.org/I112536369","display_name":"Yazd University","ror":"https://ror.org/02x99ac45","country_code":"IR","type":"education","lineage":["https://openalex.org/I112536369"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"H. R. Abutalebi","raw_affiliation_strings":["Speech Process Research Laboratory, ECE Department, Yazd University, Iran","Speech Proc. Research, Lab, ECE Dept., Yazd University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Process Research Laboratory, ECE Department, Yazd University, Iran","institution_ids":["https://openalex.org/I112536369"]},{"raw_affiliation_string":"Speech Proc. Research, Lab, ECE Dept., Yazd University","institution_ids":["https://openalex.org/I112536369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058761102","display_name":"Hamid Soltanian\u2010Zadeh","orcid":"https://orcid.org/0000-0002-7302-6856"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"H. Soltanian-Zadeh","raw_affiliation_strings":["Control and Intelligent Processing Center of Excellence, University of Tehran, Tehran, Iran","Control and Intelligent Processing Center of Excellence University of Tehran, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Control and Intelligent Processing Center of Excellence, University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]},{"raw_affiliation_string":"Control and Intelligent Processing Center of Excellence University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090489682","display_name":"Hamid Sheikhzadeh","orcid":"https://orcid.org/0000-0002-9262-4165"},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"H. Sheikhzadeh","raw_affiliation_strings":["EE Department, Amirkabir University of Technology, Tehran, Iran","EE Dept., Amirkabir University of Technology, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EE Department, Amirkabir University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I158248296"]},{"raw_affiliation_string":"EE Dept., Amirkabir University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I158248296"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.17365459,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"848","last_page":"853"},"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":0.9993000030517578,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9991999864578247,"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/binaural-recording","display_name":"Binaural recording","score":0.8209155797958374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7337518930435181},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6646470427513123},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.5908077955245972},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4618067145347595},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.4368632137775421},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4289347529411316},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4143352210521698},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37049806118011475},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.3447762131690979},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1906585395336151},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1834118664264679},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1538453996181488}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8209155797958374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7337518930435181},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6646470427513123},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.5908077955245972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4618067145347595},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.4368632137775421},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4289347529411316},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4143352210521698},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37049806118011475},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3447762131690979},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1906585395336151},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1834118664264679},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1538453996181488},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/istel.2012.6483104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/istel.2012.6483104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th International Symposium on Telecommunications (IST)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4099999964237213},{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1575829986","https://openalex.org/W1581848821","https://openalex.org/W1586342741","https://openalex.org/W1635512741","https://openalex.org/W1956364622","https://openalex.org/W1963527011","https://openalex.org/W1987906574","https://openalex.org/W2017452035","https://openalex.org/W2073375871","https://openalex.org/W2086139506","https://openalex.org/W2096554907","https://openalex.org/W2106325442","https://openalex.org/W2116594391","https://openalex.org/W2133059825","https://openalex.org/W2134162816","https://openalex.org/W2147271331","https://openalex.org/W2478526619","https://openalex.org/W3124666641","https://openalex.org/W4256399001","https://openalex.org/W6640823206","https://openalex.org/W6789284391"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W1973895194","https://openalex.org/W3135613579","https://openalex.org/W2166831097","https://openalex.org/W4386746628","https://openalex.org/W4388016426","https://openalex.org/W2546593254","https://openalex.org/W1980687383","https://openalex.org/W3209446892"],"abstract_inverted_index":{"The":[0,74],"perceptual":[1],"ability":[2],"of":[3,65,95,98,113],"the":[4,10,16,62,66,105],"human":[5],"auditory":[6],"system":[7,30,107],"in":[8,71,84,93,111],"capturing":[9],"target":[11,49],"voice":[12],"and":[13,43,76,86],"filtering":[14],"out":[15],"interferers":[17],"has":[18],"been":[19],"remained":[20],"as":[21],"a":[22,28],"great":[23],"challenge.":[24],"This":[25],"paper":[26],"proposes":[27],"binaural":[29],"for":[31,81],"speech":[32,50,114],"segregation":[33],"based":[34],"on":[35],"spatial":[36],"localization":[37],"cues:":[38],"Interaural":[39,44],"Time":[40],"Differences":[41,46],"(ITD)":[42],"Intensity":[45],"(IID).":[47],"A":[48,90],"signal":[51],"is":[52],"separated":[53],"from":[54],"interfering":[55],"sounds":[56],"by":[57],"estimating":[58],"time-frequency":[59],"masks":[60],"using":[61],"multi-level":[63],"extension":[64],"Otsu":[67],"thresholding":[68],"algorithm":[69],"used":[70],"image":[72],"segmentation.":[73],"ITD":[75],"IID":[77],"are":[78],"important":[79],"features":[80],"mask":[82],"estimation":[83],"low":[85],"high":[87],"frequencies,":[88],"respectively.":[89],"systematic":[91],"evaluation":[92],"terms":[94],"Perceptual":[96],"Evaluation":[97],"Speech":[99],"Quality":[100],"(PESQ)":[101],"index":[102],"shows":[103],"that":[104],"resulting":[106],"yields":[108],"significant":[109],"improvement":[110],"performance":[112],"separation.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}