{"id":"https://openalex.org/W1989364685","doi":"https://doi.org/10.1109/tasl.2012.2221459","title":"Exploring Monaural Features for Classification-Based Speech Segregation","display_name":"Exploring Monaural Features for Classification-Based Speech Segregation","publication_year":2012,"publication_date":"2012-10-01","ids":{"openalex":"https://openalex.org/W1989364685","doi":"https://doi.org/10.1109/tasl.2012.2221459","mag":"1989364685"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2012.2221459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2221459","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/A5100375981","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0002-3060-4345"},"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":true,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, 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":"middle","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, Ohio State Uinversity, Columbus, OH, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, 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 Uinversity, Columbus, OH, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive Science, Ohio State Uinversity, 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":3,"corresponding_author_ids":["https://openalex.org/A5100375981"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":12.1386,"has_fulltext":false,"cited_by_count":184,"citation_normalized_percentile":{"value":0.9931139,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"21","issue":"2","first_page":"270","last_page":"279"},"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":0.998199999332428,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.989799976348877,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.8083165884017944},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7294697165489197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6881189346313477},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5941847562789917},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5671859383583069},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5447027683258057},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.520788848400116},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47908836603164673},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4563610255718231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4556477665901184},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4298895299434662},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42559894919395447},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41505977511405945}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8083165884017944},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7294697165489197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6881189346313477},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5941847562789917},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5671859383583069},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5447027683258057},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.520788848400116},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47908836603164673},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4563610255718231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4556477665901184},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4298895299434662},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42559894919395447},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41505977511405945},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tasl.2012.2221459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2221459","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:10.1.1.368.1699","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.1699","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/WHW.taslp13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W10765870","https://openalex.org/W160800111","https://openalex.org/W185399533","https://openalex.org/W1635512741","https://openalex.org/W1963970749","https://openalex.org/W1964538581","https://openalex.org/W1966903391","https://openalex.org/W1979099822","https://openalex.org/W1989364685","https://openalex.org/W2013312573","https://openalex.org/W2027701650","https://openalex.org/W2027804983","https://openalex.org/W2057889776","https://openalex.org/W2063125572","https://openalex.org/W2075036909","https://openalex.org/W2090861223","https://openalex.org/W2102346872","https://openalex.org/W2106398669","https://openalex.org/W2113131123","https://openalex.org/W2113576004","https://openalex.org/W2115129089","https://openalex.org/W2128653836","https://openalex.org/W2135046866","https://openalex.org/W2137075158","https://openalex.org/W2138019504","https://openalex.org/W2143137842","https://openalex.org/W2149425615","https://openalex.org/W2150866759","https://openalex.org/W2152708632","https://openalex.org/W2155355606","https://openalex.org/W2159202424","https://openalex.org/W2159632499","https://openalex.org/W2161025448","https://openalex.org/W2166018245","https://openalex.org/W2168793898","https://openalex.org/W2273294593","https://openalex.org/W2981666567","https://openalex.org/W4231807801","https://openalex.org/W4285719527","https://openalex.org/W6607486085","https://openalex.org/W6675700563","https://openalex.org/W6684458083","https://openalex.org/W6694149276"],"related_works":["https://openalex.org/W2100772705","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/W1556565948","https://openalex.org/W2049648127"],"abstract_inverted_index":{"Monaural":[0],"speech":[1,13,99,117],"segregation":[2,14,31,118],"has":[3],"been":[4,23,46],"a":[5,16,163,172],"very":[6],"challenging":[7],"problem":[8],"for":[9,97,144],"decades.":[10],"By":[11],"casting":[12],"as":[15,48],"binary":[17],"classification":[18],"problem,":[19],"recent":[20],"advances":[21],"have":[22,45],"made":[24],"in":[25,58,91,103,129,154,171,183],"computational":[26],"auditory":[27],"scene":[28],"analysis":[29],"on":[30],"of":[32,52,156],"both":[33,184],"voiced":[34],"and":[35,41,82,105,122,131,186],"unvoiced":[36],"speech.":[37],"So":[38],"far,":[39],"pitch":[40],"amplitude":[42],"modulation":[43],"spectrogram":[44],"used":[47],"two":[49],"main":[50],"kinds":[51],"time-frequency":[53],"(T-F)":[54],"unit":[55,66],"level":[56],"features":[57,67,96,114,128,141,170],"classification.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,159],"expand":[64],"T-F":[65],"to":[68,93,147,161,167],"include":[69],"gammatone":[70],"frequency":[71],"cepstral":[72,76],"coefficients":[73],"(GFCC),":[74],"mel-frequency":[75],"coefficients,":[77],"relative":[78],"spectral":[79],"transform":[80],"(RASTA)":[81],"perceptual":[83],"linear":[84],"prediction":[85],"(PLP).":[86],"Comprehensive":[87],"comparisons":[88],"are":[89,124,142],"performed":[90],"order":[92],"identify":[94],"effective":[95],"classification-based":[98],"segregation.":[100],"Our":[101],"experiments":[102],"matched":[104,185],"unmatched":[106,187],"test":[107,133,188],"conditions":[108],"show":[109],"that":[110,139],"these":[111],"newly":[112],"included":[113],"significantly":[115],"improve":[116],"performance.":[119],"Specifically,":[120],"GFCC":[121],"RASTA-PLP":[123],"the":[125],"best":[126],"single":[127],"matched-noise":[130],"unmatched-noise":[132],"conditions,":[134],"respectively.":[135],"We":[136],"also":[137],"find":[138],"pitch-based":[140],"crucial":[143],"good":[145],"generalization":[146],"unseen":[148],"environments.":[149],"To":[150],"further":[151],"explore":[152],"complementarity":[153],"terms":[155],"discriminative":[157],"power,":[158],"propose":[160],"use":[162],"group":[164],"Lasso":[165],"approach":[166],"select":[168],"complementary":[169],"principled":[173],"way.":[174],"The":[175],"final":[176],"combined":[177],"feature":[178],"set":[179],"yields":[180],"promising":[181],"results":[182],"conditions.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":18},{"year":2016,"cited_by_count":17},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":20},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}