{"id":"https://openalex.org/W2166018245","doi":"https://doi.org/10.1109/icassp.2011.5947387","title":"An SVM based classification approach to speech separation","display_name":"An SVM based classification approach to speech separation","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2166018245","doi":"https://doi.org/10.1109/icassp.2011.5947387","mag":"2166018245"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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 of Cognitive Science, Ohio State Uinversity, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & Center of Cognitive Science, Ohio State Uinversity, 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 & Center of Cognitive Science, Ohio State Uinversity, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & Center of Cognitive Science, Ohio State Uinversity, 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":null,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4632","last_page":"4635"},"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":0.9988999962806702,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.8723915815353394},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.759198009967804},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7234348058700562},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.6376737356185913},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6373189687728882},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6353459358215332},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5406988859176636},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.5395312905311584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5278877019882202},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4870210289955139},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.470737099647522},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4593532383441925},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.43743765354156494},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43709880113601685},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4194965362548828},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2296239137649536},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17686781287193298},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1130569577217102},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08604887127876282}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8723915815353394},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.759198009967804},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7234348058700562},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.6376737356185913},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6373189687728882},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6353459358215332},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5406988859176636},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5395312905311584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5278877019882202},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4870210289955139},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.470737099647522},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4593532383441925},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.43743765354156494},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43709880113601685},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4194965362548828},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2296239137649536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17686781287193298},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1130569577217102},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08604887127876282},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.324","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.324","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/Han-Wang.icassp11.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1963970749","https://openalex.org/W1979099822","https://openalex.org/W2034040413","https://openalex.org/W2042750879","https://openalex.org/W2055246866","https://openalex.org/W2057889776","https://openalex.org/W2108564850","https://openalex.org/W2122982914","https://openalex.org/W2123157731","https://openalex.org/W2153635508","https://openalex.org/W2561557072","https://openalex.org/W2981666567","https://openalex.org/W3120421331","https://openalex.org/W3216401400","https://openalex.org/W4231807801","https://openalex.org/W4233392025","https://openalex.org/W6769316794"],"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/W2538939196"],"abstract_inverted_index":{"Monaural":[0],"speech":[1,50],"separation":[2,29],"is":[3,79],"a":[4,15,24,62,99],"very":[5],"challenging":[6],"task.":[7],"CASA-based":[8],"systems":[9],"utilize":[10],"acoustic":[11],"features":[12,37],"to":[13,27,65,82],"produce":[14],"time-frequency":[16],"(T-F)":[17],"mask.":[18],"In":[19],"this":[20],"study,":[21],"we":[22],"propose":[23],"classification":[25,105],"approach":[26,91],"monaural":[28],"problem.":[30],"Our":[31],"feature":[32],"set":[33],"consists":[34],"of":[35,104],"pitch-based":[36],"and":[38,48,97],"amplitude":[39],"modulation":[40],"spectrum":[41],"features,":[42],"which":[43],"can":[44],"discriminate":[45],"both":[46],"voiced":[47],"unvoiced":[49],"from":[51],"nonspeech":[52],"interference.":[53],"We":[54],"employ":[55],"support":[56],"vector":[57],"machines":[58],"(SVMs)":[59],"followed":[60],"by":[61],"re-thresholding":[63],"method":[64],"classify":[66],"each":[67],"T-F":[68],"unit":[69],"as":[70],"either":[71],"target-dominated":[72],"or":[73],"interference-dominated.":[74],"An":[75],"auditory":[76],"segmentation":[77],"stage":[78],"then":[80],"utilized":[81],"improve":[83],"SVM-generated":[84],"results.":[85],"Systematic":[86],"evaluations":[87],"show":[88],"that":[89],"our":[90],"produces":[92],"high":[93],"quality":[94],"binary":[95],"masks":[96],"outperforms":[98],"previous":[100],"system":[101],"in":[102],"terms":[103],"accuracy.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}