{"id":"https://openalex.org/W1639266067","doi":"https://doi.org/10.1109/icassp.2003.1202330","title":"Co-channel speaker identification using usable speech extraction based on multi-pitch tracking","display_name":"Co-channel speaker identification using usable speech extraction based on multi-pitch tracking","publication_year":2003,"publication_date":"2003-12-22","ids":{"openalex":"https://openalex.org/W1639266067","doi":"https://doi.org/10.1109/icassp.2003.1202330","mag":"1639266067"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1202330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202330","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5079984408","display_name":"Yang Shao","orcid":"https://orcid.org/0000-0002-4870-7406"},"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":"Yang Shao","raw_affiliation_strings":["Department of Computer and Information Science & Center of Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","Dept of Comput. & Inf. Sci., Ohio State Univ., Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science & Center of Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept of Comput. & Inf. Sci., Ohio State Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101752802","display_name":"Deliang Wang","orcid":"https://orcid.org/0009-0008-6488-0234"},"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, Columbus, OH, USA","Dept of Comput. & Inf. Sci., Ohio State Univ., Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science & Center of Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept of Comput. & Inf. Sci., Ohio State Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079984408"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":4.2753,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.95230999,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2","issue":null,"first_page":"II","last_page":"205"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.996999979019165,"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":0.996999979019165,"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":0.991599977016449,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9732999801635742,"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/usable","display_name":"USable","score":0.9121407270431519},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7767760753631592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7688097953796387},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.6401225924491882},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6364409327507019},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5545687079429626},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5070748329162598},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.49415138363838196},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45865389704704285},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.43765825033187866},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0816929042339325}],"concepts":[{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.9121407270431519},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7767760753631592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688097953796387},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.6401225924491882},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6364409327507019},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5545687079429626},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5070748329162598},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.49415138363838196},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45865389704704285},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.43765825033187866},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0816929042339325},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2003.1202330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202330","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.128.7429","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.128.7429","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/Shao-Wang.icassp03.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W29573733","https://openalex.org/W29805274","https://openalex.org/W264546557","https://openalex.org/W1951870577","https://openalex.org/W2044222806","https://openalex.org/W2115896199","https://openalex.org/W2170491071","https://openalex.org/W6609760517"],"related_works":["https://openalex.org/W2532162280","https://openalex.org/W4251579108","https://openalex.org/W4234190324","https://openalex.org/W127975155","https://openalex.org/W2224782519","https://openalex.org/W3104257531","https://openalex.org/W2126085626","https://openalex.org/W2545131480","https://openalex.org/W1973693762","https://openalex.org/W208363076"],"abstract_inverted_index":{"Recently,":[0],"usable":[1,26],"speech":[2,11,27,58,76],"criteria":[3],"have":[4,61],"been":[5],"proposed":[6],"to":[7,30,55,86],"extract":[8],"minimally":[9],"corrupted":[10],"for":[12,90],"speaker":[13,91],"identification":[14],"(SID)":[15],"in":[16],"co-channel":[17,37,75],"speech.":[18],"In":[19],"this":[20],"paper,":[21],"we":[22],"propose":[23],"a":[24,46,80],"new":[25],"extraction":[28],"method":[29],"improve":[31],"the":[32,36,41,57,68],"SID":[33],"performance":[34],"under":[35],"situation":[38],"based":[39],"on":[40,74],"pitch":[42,64],"information":[43],"obtained":[44],"from":[45],"robust":[47],"multi-pitch":[48],"tracking":[49],"algorithm":[50],"[2].":[51],"The":[52,70],"idea":[53],"is":[54,72],"retain":[56],"segments":[59],"that":[60],"only":[62],"one":[63],"detected":[65],"and":[66,77],"remove":[67],"others.":[69],"system":[71],"evaluated":[73],"results":[78],"show":[79],"significant":[81],"improvement":[82],"across":[83],"various":[84],"target":[85],"interferer":[87],"ratios":[88],"(TIR)":[89],"identification.":[92]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
