{"id":"https://openalex.org/W2080680098","doi":"https://doi.org/10.1109/icassp.2002.5743777","title":"Monaural speech segregation based on pitch tracking and amplitude modulation","display_name":"Monaural speech segregation based on pitch tracking and amplitude modulation","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2080680098","doi":"https://doi.org/10.1109/icassp.2002.5743777","mag":"2080680098"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743777","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-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/A5112457807","display_name":"Guoning Hu","orcid":null},"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":"Guoning Hu","raw_affiliation_strings":["Ohio State Uinversity, USA","Biophysics Program, The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Ohio State Uinversity, USA","institution_ids":[]},{"raw_affiliation_string":"Biophysics Program, The Ohio State University, 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 and Information Science & Center of Cognitive Science, Ohio State Uinversity, USA","Department of Computer and Information Science & Center of Cognitive Science, The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science & Center of Cognitive Science, Ohio State Uinversity, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer and Information Science & Center of Cognitive Science, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112457807"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.9898,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.69289991,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"553"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9994000196456909,"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":0.8901330232620239},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.7807544469833374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7048623561859131},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.6632108688354492},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6463780403137207},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.5721128582954407},{"id":"https://openalex.org/keywords/auditory-system","display_name":"Auditory system","score":0.5604810118675232},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5098394751548767},{"id":"https://openalex.org/keywords/harmonics","display_name":"Harmonics","score":0.4929192066192627},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.4905065894126892},{"id":"https://openalex.org/keywords/amplitude-modulation","display_name":"Amplitude modulation","score":0.45436790585517883},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.4373264014720917},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42651334404945374},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.424099862575531},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41166555881500244},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3461505174636841},{"id":"https://openalex.org/keywords/radio-frequency","display_name":"Radio frequency","score":0.18815070390701294},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10391572117805481},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0861051082611084},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08117431402206421}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8901330232620239},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.7807544469833374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7048623561859131},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.6632108688354492},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6463780403137207},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.5721128582954407},{"id":"https://openalex.org/C2777443451","wikidata":"https://www.wikidata.org/wiki/Q821413","display_name":"Auditory system","level":2,"score":0.5604810118675232},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5098394751548767},{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.4929192066192627},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.4905065894126892},{"id":"https://openalex.org/C201905106","wikidata":"https://www.wikidata.org/wiki/Q183755","display_name":"Amplitude modulation","level":4,"score":0.45436790585517883},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.4373264014720917},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42651334404945374},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.424099862575531},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41166555881500244},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3461505174636841},{"id":"https://openalex.org/C74064498","wikidata":"https://www.wikidata.org/wiki/Q3396184","display_name":"Radio frequency","level":2,"score":0.18815070390701294},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10391572117805481},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0861051082611084},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08117431402206421},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2002.5743777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743777","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.124.298","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.124.298","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.waspaa01.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.130.519","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.130.519","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.icassp02.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.134.6283","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.134.6283","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.tnn04.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/16"},{"display_name":"Reduced inequalities","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1567997379","https://openalex.org/W1575829986","https://openalex.org/W2013020033","https://openalex.org/W2044222806","https://openalex.org/W2074354966","https://openalex.org/W2085085647","https://openalex.org/W2097191389","https://openalex.org/W2225904595","https://openalex.org/W2485688913","https://openalex.org/W2949897626","https://openalex.org/W3023341514","https://openalex.org/W4256399001"],"related_works":["https://openalex.org/W2550493152","https://openalex.org/W1653463454","https://openalex.org/W2759822254","https://openalex.org/W1996379799","https://openalex.org/W1539684593","https://openalex.org/W2376500725","https://openalex.org/W3199891340","https://openalex.org/W1008356495","https://openalex.org/W2474557191","https://openalex.org/W578103756"],"abstract_inverted_index":{"Monaural":[0],"speech":[1,54,124],"segregation":[2,55],"remains":[3],"a":[4,51,115],"computational":[5,17],"challenge":[6],"for":[7,15,53],"auditory":[8,18],"scene":[9,19],"analysis":[10,20],"(ASA).":[11],"A":[12],"major":[13],"problem":[14],"existing":[16],"(CASA)":[21],"systems":[22],"is":[23,114,119,137],"their":[24],"inability":[25],"to":[26,43,82,99,106],"deal":[27],"with":[28,58],"signals":[29,62],"in":[30,97,151],"the":[31,87,111,152],"high-frequency":[32,61,85,153],"range.":[33,154],"Psychoacoustic":[34],"evidence":[35],"suggests":[36],"that":[37,56,118],"different":[38],"perceptual":[39],"mechanisms":[40],"are":[41],"involved":[42],"handle":[44],"resolved":[45],"and":[46,60,75,78,102,129,140],"unresolved":[47],"harmonics.":[48],"We":[49],"propose":[50],"system":[52,136],"deals":[57],"low-frequency":[59,65],"differently.":[63],"For":[64,84],"signals,":[66],"our":[67],"model":[68,88],"generates":[69,89],"segments":[70,90],"based":[71,91,125],"on":[72,92,126],"temporal":[73,100],"continuity":[74],"cross-channel":[76],"correlation,":[77],"groups":[79,103],"them":[80,104],"according":[81,105],"periodicity.":[83],"signals.":[86],"common":[93],"amplitude":[94],"modulation":[95],"(AM)":[96],"addition":[98],"continuity,":[101],"AM":[107],"repetition":[108],"rates.":[109],"Underlying":[110],"grouping":[112],"process":[113],"pitch":[116,128],"contour":[117],"first":[120],"estimated":[121],"from":[122],"segregated":[123],"global":[127],"then":[130],"verified":[131],"by":[132],"psychoacoustic":[133],"constraints.":[134],"Our":[135],"systematically":[138],"evaluated,":[139],"it":[141],"yields":[142],"substantially":[143],"better":[144],"performance":[145],"than":[146],"previous":[147],"CASA":[148],"systems,":[149],"especially":[150]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}