{"id":"https://openalex.org/W1637094848","doi":"https://doi.org/10.1109/taslp.2015.2479039","title":"Supervised Single-Microphone Multi-Talker Speech Separation with Conditional Random Fields","display_name":"Supervised Single-Microphone Multi-Talker Speech Separation with Conditional Random Fields","publication_year":2015,"publication_date":"2015-09-15","ids":{"openalex":"https://openalex.org/W1637094848","doi":"https://doi.org/10.1109/taslp.2015.2479039","mag":"1637094848"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2479039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2479039","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM 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/A5083831776","display_name":"Yu Ting Yeung","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yu Ting Yeung","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong, SAR of China","Stanley Ho Big Data Decision Analytics Research Centre, The Chinese University of Hong Kong, Hong Kong, China and Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong, SAR of China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Stanley Ho Big Data Decision Analytics Research Centre, The Chinese University of Hong Kong, Hong Kong, China and Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong, SAR of China","Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong, SAR of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong, SAR of China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong, SAR of China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113828649","display_name":"Cheung-Chi Leung","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Cheung-Chi Leung","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, Singapore","Human Language Technol. Dept., Inst. for Infocomm Res., Singapore#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Human Language Technol. Dept., Inst. for Infocomm Res., Singapore#TAB#","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2899,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53819165,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"23","issue":"12","first_page":"2334","last_page":"2342"},"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":0.9983000159263611,"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":0.9958000183105469,"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/conditional-random-field","display_name":"Conditional random field","score":0.6876357197761536},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6353684663772583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6135050058364868},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5538027286529541},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5293543934822083},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4463047683238983},{"id":"https://openalex.org/keywords/crfs","display_name":"CRFS","score":0.4454188048839569},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4351697862148285},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4351426064968109},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40703415870666504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3799958825111389},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.21914276480674744}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6876357197761536},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6353684663772583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6135050058364868},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5538027286529541},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5293543934822083},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4463047683238983},{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.4454188048839569},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4351697862148285},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4351426064968109},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40703415870666504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3799958825111389},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.21914276480674744},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2015.2479039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2479039","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G3896125329","display_name":"Periodicity Enhancement and Phonemic Restoration for Improving Speech Perception by Hearing Impaired Listeners","funder_award_id":"413811","funder_id":"https://openalex.org/F4320321592","funder_display_name":"Research Grants Council, University Grants Committee"},{"id":"https://openalex.org/G5229569371","display_name":null,"funder_award_id":"CUHK 414010","funder_id":"https://openalex.org/F4320321592","funder_display_name":"Research Grants Council, University Grants Committee"},{"id":"https://openalex.org/G7893511035","display_name":"Objective assessment of pathological voices based on acoustic signal analysis and classification","funder_award_id":"14204014","funder_id":"https://openalex.org/F4320321592","funder_display_name":"Research Grants Council, University Grants Committee"}],"funders":[{"id":"https://openalex.org/F4320321592","display_name":"Research Grants Council, University Grants Committee","ror":"https://ror.org/00djwmt25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W174003511","https://openalex.org/W185399533","https://openalex.org/W1496562625","https://openalex.org/W1528056001","https://openalex.org/W1560512119","https://openalex.org/W1877570817","https://openalex.org/W1902027874","https://openalex.org/W1967896185","https://openalex.org/W1989954041","https://openalex.org/W2004826498","https://openalex.org/W2015143272","https://openalex.org/W2029414441","https://openalex.org/W2031647436","https://openalex.org/W2036245667","https://openalex.org/W2059833849","https://openalex.org/W2069681747","https://openalex.org/W2086161653","https://openalex.org/W2086725969","https://openalex.org/W2087334523","https://openalex.org/W2096920988","https://openalex.org/W2098678088","https://openalex.org/W2100966557","https://openalex.org/W2102804087","https://openalex.org/W2103135337","https://openalex.org/W2103945478","https://openalex.org/W2105644991","https://openalex.org/W2105892554","https://openalex.org/W2109886546","https://openalex.org/W2120340025","https://openalex.org/W2121973264","https://openalex.org/W2127851351","https://openalex.org/W2130322773","https://openalex.org/W2132038425","https://openalex.org/W2134807719","https://openalex.org/W2138939691","https://openalex.org/W2147880316","https://openalex.org/W2150142469","https://openalex.org/W2150415460","https://openalex.org/W2152463966","https://openalex.org/W2156515921","https://openalex.org/W2156615793","https://openalex.org/W2163614729","https://openalex.org/W2168554752","https://openalex.org/W2168793898","https://openalex.org/W2317707553","https://openalex.org/W2403697053","https://openalex.org/W2405589348","https://openalex.org/W2471103604","https://openalex.org/W2604272474","https://openalex.org/W2612972698","https://openalex.org/W2990138404","https://openalex.org/W2999905431","https://openalex.org/W3147539069","https://openalex.org/W4245919820","https://openalex.org/W4293052541","https://openalex.org/W6607486085","https://openalex.org/W6633434192","https://openalex.org/W6675041964","https://openalex.org/W6682082992","https://openalex.org/W6682238262","https://openalex.org/W6713310157","https://openalex.org/W6713519970"],"related_works":["https://openalex.org/W2055466819","https://openalex.org/W50079190","https://openalex.org/W2356597680","https://openalex.org/W182104056","https://openalex.org/W2111726165","https://openalex.org/W2011251309","https://openalex.org/W2796133761","https://openalex.org/W3088215229","https://openalex.org/W2511246383","https://openalex.org/W2184553228"],"abstract_inverted_index":{"We":[0,15,136],"apply":[1],"conditional":[2],"random":[3],"field":[4],"(CRF)":[5],"for":[6],"single-microphone":[7],"speech":[8,53,57,110],"separation":[9],"in":[10,22],"a":[11,139],"supervised":[12],"learning":[13],"scenario.":[14],"train":[16],"the":[17,24,29,42,61,86,90,97,101,109,128,151,156],"parameters":[18],"with":[19,28,35,92,123],"mixture":[20,48,71,111],"data":[21,49,72],"which":[23],"sources":[25,91],"are":[26,73],"competing":[27],"same":[30,152],"average":[31],"signal":[32],"power.":[33],"Compared":[34],"factorial":[36,118],"hidden":[37],"Markov":[38],"model":[39,134],"(HMM)":[40],"baselines,":[41],"CRF":[43,76,129,158],"settings":[44,77,130,159],"require":[45],"fewer":[46],"training":[47,68],"to":[50,132],"improve":[51],"objective":[52],"quality":[54],"measures":[55],"and":[56,69,124],"recognition":[58],"accuracy":[59],"of":[60,67,89],"reconstructed":[62],"sources,":[63],"when":[64],"mixing":[65,81,102],"ratios":[66],"testing":[70],"matched.":[74],"The":[75,148],"also":[78,137],"handle":[79],"minor":[80],"ratio":[82,103],"mismatch":[83,104],"after":[84,160],"adjusting":[85],"gain":[87],"factors":[88],"non-linear":[93],"mappings":[94],"inspired":[95],"from":[96],"mixture-maximization":[98],"model.":[99],"When":[100],"further":[105],"increases":[106],"such":[107],"that":[108],"is":[112],"dominated":[113],"by":[114],"only":[115],"one":[116],"source,":[117],"HMM":[119],"finally":[120],"catches":[121],"up":[122],"performs":[125],"better":[126],"than":[127],"due":[131],"improved":[133],"accuracy.":[135],"develop":[138],"convex":[140],"statistical":[141],"inference":[142],"simplification":[143,149],"based":[144],"on":[145],"linear-chain":[146],"CRFs.":[147],"achieves":[150],"performance":[153],"level":[154],"as":[155],"original":[157],"integrating":[161],"additional":[162],"observations.":[163]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}