{"id":"https://openalex.org/W2161865195","doi":"https://doi.org/10.1109/icassp.2012.6288929","title":"SVM-based separation of unvoiced-voiced speech in cochannel conditions","display_name":"SVM-based separation of unvoiced-voiced speech in cochannel conditions","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2161865195","doi":"https://doi.org/10.1109/icassp.2012.6288929","mag":"2161865195"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288929","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288929","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/A5110092110","display_name":"Ke Hu","orcid":"https://orcid.org/0009-0003-0835-5893"},"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, The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, 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, The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, 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":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"51","issue":null,"first_page":"4545","last_page":"4548"},"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":0.9972000122070312,"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":0.9965999722480774,"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/timit","display_name":"TIMIT","score":0.890697717666626},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8017281889915466},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7017350196838379},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6181170344352722},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6074855923652649},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5214904546737671},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5167588591575623},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48657047748565674},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4557700753211975},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44320806860923767},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.43432775139808655},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43299174308776855},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43086421489715576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3758760690689087},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.28793513774871826},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10728830099105835}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.890697717666626},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8017281889915466},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7017350196838379},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6181170344352722},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6074855923652649},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5214904546737671},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5167588591575623},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48657047748565674},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4557700753211975},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44320806860923767},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.43432775139808655},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43299174308776855},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43086421489715576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3758760690689087},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.28793513774871826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10728830099105835},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6288929","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288929","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.585","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.585","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.icassp12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320336555","display_name":"Garron Family Cancer Centre","ror":null},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1635512741","https://openalex.org/W1963970749","https://openalex.org/W1979815907","https://openalex.org/W2013312573","https://openalex.org/W2027804983","https://openalex.org/W2079362249","https://openalex.org/W2115129089","https://openalex.org/W2119901478","https://openalex.org/W2120933697","https://openalex.org/W2122982914","https://openalex.org/W2124149378","https://openalex.org/W2139212933","https://openalex.org/W2153635508","https://openalex.org/W2159202424","https://openalex.org/W2166018245","https://openalex.org/W3120421331","https://openalex.org/W3127686677","https://openalex.org/W3216401400","https://openalex.org/W4233392025"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961","https://openalex.org/W2413040788"],"abstract_inverted_index":{"Unvoiced-voiced":[0],"portions":[1],"of":[2,8,27,46,60],"cochannel":[3],"speech":[4,13,28,39,107],"contain":[5],"considerable":[6],"amounts":[7],"both":[9],"voiced":[10],"and":[11,14,49,72],"unvoiced":[12,106],"play":[15],"a":[16,34,61,111],"significant":[17],"role":[18],"in":[19,25],"separation.":[20,40],"Motivated":[21],"by":[22],"recent":[23,112],"developments":[24],"separation":[26],"from":[29],"nonspeech":[30],"noise,":[31],"we":[32],"propose":[33],"classification-based":[35],"approach":[36],"for":[37,91],"unvoiced-voiced":[38],"A":[41],"new":[42],"feature":[43],"set":[44],"consisting":[45],"pitch-based":[47,79],"features":[48,66,80],"gammatone":[50],"frequency":[51],"cepstral":[52,65],"coefficients":[53],"is":[54],"proposed":[55,102],"to":[56,81,110],"represent":[57],"the":[58,78,96,101],"characteristics":[59],"time-frequency":[62],"unit.":[63],"The":[64],"do":[67],"not":[68],"rely":[69],"on":[70,95],"pitch":[71,82],"are":[73,89],"thus":[74],"more":[75],"robust":[76],"than":[77],"estimation":[83],"errors.":[84],"Speaker-independent":[85],"support":[86],"vector":[87],"machines":[88],"trained":[90],"classification.":[92],"Results":[93],"based":[94],"TIMIT":[97],"corpus":[98],"show":[99],"that":[100],"algorithm":[103],"significantly":[104],"improves":[105],"segregation":[108],"compared":[109],"algorithm.":[113]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}