{"id":"https://openalex.org/W2144110073","doi":"https://doi.org/10.1109/icassp.2012.6288928","title":"On generalization of classification based speech separation","display_name":"On generalization of classification based speech separation","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2144110073","doi":"https://doi.org/10.1109/icassp.2012.6288928","mag":"2144110073"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101924647","display_name":"Kun Han","orcid":"https://orcid.org/0000-0003-2148-7594"},"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":"Kun Han","raw_affiliation_strings":["Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, OH, USA","[Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, 43210-1277, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"[Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, 43210-1277, 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 & Center for Cognitive Science, The Ohio State University, Columbus, OH, USA","[Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, 43210-1277, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"[Department of Computer Science and Engineering & Center for Cognitive Science, The Ohio State University, Columbus, 43210-1277, 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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":null,"first_page":"4541","last_page":"4544"},"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":0.9987999796867371,"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":0.9987000226974487,"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/generalization","display_name":"Generalization","score":0.751409649848938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7423465251922607},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.66748046875},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.6108182668685913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5914822220802307},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5487636923789978},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.5179661512374878},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.514094889163971},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5107157230377197},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.45387497544288635},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4474916458129883},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4450169503688812},{"id":"https://openalex.org/keywords/binary-decision-diagram","display_name":"Binary decision diagram","score":0.443087100982666},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.402029812335968},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2445182204246521},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1624184250831604},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.152712881565094}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.751409649848938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423465251922607},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.66748046875},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.6108182668685913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5914822220802307},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5487636923789978},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5179661512374878},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.514094889163971},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5107157230377197},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.45387497544288635},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4474916458129883},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4450169503688812},{"id":"https://openalex.org/C3309909","wikidata":"https://www.wikidata.org/wiki/Q864155","display_name":"Binary decision diagram","level":2,"score":0.443087100982666},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.402029812335968},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2445182204246521},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1624184250831604},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.152712881565094},{"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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1618905105","https://openalex.org/W1963970749","https://openalex.org/W1979099822","https://openalex.org/W2027804983","https://openalex.org/W2042750879","https://openalex.org/W2057889776","https://openalex.org/W2122982914","https://openalex.org/W2129120544","https://openalex.org/W2137075158","https://openalex.org/W2153635508","https://openalex.org/W2166018245","https://openalex.org/W2561557072","https://openalex.org/W3120421331","https://openalex.org/W4231807801","https://openalex.org/W4233392025","https://openalex.org/W6636501900"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W4321794819","https://openalex.org/W2072124114","https://openalex.org/W2944394647","https://openalex.org/W4378976585"],"abstract_inverted_index":{"Monaural":[0],"speech":[1],"separation":[2],"is":[3,42,85,99],"a":[4,26,51,74],"very":[5],"challenging":[6],"problem.":[7,24],"Recent":[8],"studies":[9],"utilize":[10],"supervised":[11,27],"learning":[12,28],"methods":[13,47],"to":[14,21,34,58,67,77,87,101],"estimate":[15,78],"the":[16,23,30,79,110],"ideal":[17],"binary":[18],"mask":[19],"(IBM)":[20],"solve":[22],"In":[25],"framework,":[29],"issue":[31],"of":[32],"generalization":[33],"conditions":[35,92],"different":[36],"from":[37],"those":[38],"used":[39,86,100],"in":[40],"training":[41,53],"paramount.":[43],"This":[44],"paper":[45],"describes":[46],"that":[48,109],"require":[49],"only":[50],"small":[52],"corpus":[54],"but":[55],"can":[56],"generalize":[57],"unseen":[59,89,103,119],"conditions.":[60,105,120],"The":[61],"system":[62],"utilizes":[63],"support":[64],"vector":[65],"machines":[66],"learn":[68],"classification":[69],"cues":[70],"and":[71,93],"then":[72],"employs":[73],"rethresholding":[75],"method":[76,84],"IBM.":[80],"A":[81],"distribution":[82],"fitting":[83],"address":[88,102],"signal-to-noise":[90],"ratio":[91],"an":[94],"iterative":[95],"voice":[96],"activity":[97],"detection":[98],"noise":[104],"Systematic":[106],"evaluations":[107],"show":[108],"proposed":[111],"approach":[112],"produces":[113],"high":[114],"quality":[115],"IBM":[116],"estimates":[117],"under":[118]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
