{"id":"https://openalex.org/W2088361146","doi":"https://doi.org/10.1109/tasl.2012.2215591","title":"An Unsupervised Approach to Cochannel Speech Separation","display_name":"An Unsupervised Approach to Cochannel Speech Separation","publication_year":2012,"publication_date":"2012-09-15","ids":{"openalex":"https://openalex.org/W2088361146","doi":"https://doi.org/10.1109/tasl.2012.2215591","mag":"2088361146"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2012.2215591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2215591","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5087874570","display_name":"Ke Hu","orcid":"https://orcid.org/0000-0002-0511-968X"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Hu","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering and the Center for Cognitive Science, Ohio State University, Columbus, OH, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive Science, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":4.8736,"has_fulltext":false,"cited_by_count":96,"citation_normalized_percentile":{"value":0.9688367,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"21","issue":"1","first_page":"122","last_page":"131"},"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/T11309","display_name":"Music and Audio Processing","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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.7405133843421936},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6900838613510132},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.652553915977478},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5281534194946289},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5251162648200989},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.49633342027664185},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4881230294704437},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.47062209248542786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4486003518104553},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.43575191497802734},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1458878517150879}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7405133843421936},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6900838613510132},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.652553915977478},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5281534194946289},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5251162648200989},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.49633342027664185},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4881230294704437},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.47062209248542786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4486003518104553},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.43575191497802734},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1458878517150879},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tasl.2012.2215591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2215591","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.2648","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.2648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~dwang/papers/Hu-Wang.taslp13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.550000011920929,"display_name":"Peace, Justice and strong institutions"},{"id":"https://metadata.un.org/sdg/10","score":0.4699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W140549394","https://openalex.org/W185399533","https://openalex.org/W1508694032","https://openalex.org/W1574263887","https://openalex.org/W1902027874","https://openalex.org/W1963835294","https://openalex.org/W1975152892","https://openalex.org/W1979815907","https://openalex.org/W2013312573","https://openalex.org/W2048462764","https://openalex.org/W2072184010","https://openalex.org/W2075036909","https://openalex.org/W2079362249","https://openalex.org/W2086725969","https://openalex.org/W2091766358","https://openalex.org/W2096705927","https://openalex.org/W2111070087","https://openalex.org/W2119901478","https://openalex.org/W2120933697","https://openalex.org/W2123157731","https://openalex.org/W2124149378","https://openalex.org/W2125562558","https://openalex.org/W2136091744","https://openalex.org/W2149425615","https://openalex.org/W2150269104","https://openalex.org/W2157906748","https://openalex.org/W2159202424","https://openalex.org/W2159591770","https://openalex.org/W2170491071","https://openalex.org/W3216401400","https://openalex.org/W6607486085","https://openalex.org/W6630391810","https://openalex.org/W6680180052","https://openalex.org/W6682080839"],"related_works":["https://openalex.org/W2394327295","https://openalex.org/W2358941527","https://openalex.org/W2033914206","https://openalex.org/W2146076056","https://openalex.org/W2163831990","https://openalex.org/W3003836766","https://openalex.org/W2046077695","https://openalex.org/W2005437358","https://openalex.org/W2378160586","https://openalex.org/W2123157731"],"abstract_inverted_index":{"Cochannel":[0],"(two-talker)":[1],"speech":[2,41,90],"separation":[3],"is":[4,62],"predominantly":[5],"addressed":[6],"using":[7,100],"pretrained":[8],"speaker":[9,75],"dependent":[10],"models.":[11],"In":[12],"this":[13],"paper,":[14],"we":[15,86],"propose":[16],"an":[17],"unsupervised":[18,55],"approach":[19,25,113],"to":[20,67,132],"separating":[21],"cochannel":[22],"speech.":[23,108],"Our":[24],"follows":[26],"the":[27,43,69,101],"two":[28],"main":[29],"stages":[30],"of":[31,71,105,121],"computational":[32],"auditory":[33],"scene":[34],"analysis:":[35],"segmentation":[36],"and":[37,53,73,135],"grouping.":[38,59],"For":[39],"voiced":[40,107],"segregation,":[42],"proposed":[44,125],"system":[45,126],"utilizes":[46],"a":[47,65,119],"tandem":[48],"algorithm":[49],"for":[50,57],"simultaneous":[51],"grouping":[52],"then":[54],"clustering":[56,61],"sequential":[58],"The":[60,96,124],"performed":[63],"by":[64],"search":[66],"maximize":[68],"ratio":[70],"between-":[72],"within-group":[74,79],"distances":[76],"while":[77],"penalizing":[78],"concurrent":[80],"pitches.":[81],"To":[82],"segregate":[83],"unvoiced":[84,89],"speech,":[85],"first":[87],"produce":[88],"segments":[91,97],"based":[92],"on":[93],"onset/offset":[94],"analysis.":[95],"are":[98],"grouped":[99],"complementary":[102],"binary":[103],"masks":[104],"segregated":[106],"Despite":[109],"its":[110],"simplicity,":[111],"our":[112],"produces":[114],"significant":[115],"SNR":[116],"improvements":[117],"across":[118],"range":[120],"input":[122],"SNR.":[123],"yields":[127],"competitive":[128],"performance":[129],"in":[130],"comparison":[131],"other":[133],"speaker-independent":[134],"model-based":[136],"methods.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}