{"id":"https://openalex.org/W4366503942","doi":"https://doi.org/10.1109/taslp.2023.3268572","title":"Speaker Counting and Separation From Single-Channel Noisy Mixtures","display_name":"Speaker Counting and Separation From Single-Channel Noisy Mixtures","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4366503942","doi":"https://doi.org/10.1109/taslp.2023.3268572"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3268572","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3268572","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10105940.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10105940.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004929413","display_name":"Srikanth Raj Chetupalli","orcid":"https://orcid.org/0000-0002-2186-5420"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Srikanth Raj Chetupalli","raw_affiliation_strings":["International Audio Laboratories, A Joint Institution of the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) and Fraunhofer IIS, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2186-5420","affiliations":[{"raw_affiliation_string":"International Audio Laboratories, A Joint Institution of the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) and Fraunhofer IIS, Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192","https://openalex.org/I4210124274"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031626756","display_name":"Emanu\u00ebl A. P. Habets","orcid":"https://orcid.org/0000-0002-2613-8046"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Emanu\u00ebl A. P. Habets","raw_affiliation_strings":["International Audio Laboratories, A Joint Institution of the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) and Fraunhofer IIS, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2613-8046","affiliations":[{"raw_affiliation_string":"International Audio Laboratories, A Joint Institution of the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) and Fraunhofer IIS, Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192","https://openalex.org/I4210124274"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5105,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.93661013,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"1681","last_page":"1692"},"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":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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/speech-recognition","display_name":"Speech recognition","score":0.7252696752548218},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6907783150672913},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5080047249794006},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4834080934524536},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.43980634212493896},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4284452199935913},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38895660638809204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34920865297317505}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7252696752548218},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6907783150672913},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5080047249794006},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4834080934524536},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.43980634212493896},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4284452199935913},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38895660638809204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34920865297317505},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2023.3268572","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3268572","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10105940.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/450459","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/450459","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2023.3268572","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3268572","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10105940.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4366503942.pdf","grobid_xml":"https://content.openalex.org/works/W4366503942.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1790748249","https://openalex.org/W2127851351","https://openalex.org/W2407080277","https://openalex.org/W2407685581","https://openalex.org/W2734774145","https://openalex.org/W2763188033","https://openalex.org/W2884225676","https://openalex.org/W2889519245","https://openalex.org/W2891054259","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962728945","https://openalex.org/W2962935966","https://openalex.org/W2972541922","https://openalex.org/W2972767900","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3035268204","https://openalex.org/W3095212884","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3124794156","https://openalex.org/W3160408143","https://openalex.org/W3161301466","https://openalex.org/W3162629387","https://openalex.org/W3163652268","https://openalex.org/W3167533889","https://openalex.org/W3185109982","https://openalex.org/W3205004157","https://openalex.org/W4210702413","https://openalex.org/W4297841822","https://openalex.org/W4385245566","https://openalex.org/W6714030504","https://openalex.org/W6739901393","https://openalex.org/W6774995033","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2386387936","https://openalex.org/W2033914206","https://openalex.org/W2015574505","https://openalex.org/W2355125052","https://openalex.org/W2040365831","https://openalex.org/W2020163257","https://openalex.org/W4378805784","https://openalex.org/W2485008119","https://openalex.org/W2076268407","https://openalex.org/W1496294449"],"abstract_inverted_index":{"We":[0,45,149],"address":[1],"the":[2,17,20,65,89,92,136,146,152,166],"problem":[3],"of":[4,16,58,75,84,123,135,172],"speaker":[5,56,68,71,156],"counting":[6,157],"and":[7,42,63,70,87,94,142,159],"separation":[8],"from":[9,139,145],"a":[10,47,55,102,120],"noisy,":[11],"single-channel,":[12],"multi-source,":[13],"recording.":[14],"Most":[15],"works":[18],"in":[19,101,165],"literature":[21],"assume":[22],"mixtures":[23,36,74,133,171],"containing":[24],"two":[25],"to":[26,39,77,99,118,174],"five":[27,40,78],"speakers.":[28,79,176],"In":[29],"this":[30],"work,":[31],"we":[32],"consider":[33],"noisy":[34,131],"speech":[35,132,137],"with":[37,113,129],"one":[38,76],"speakers":[41],"noise-only":[43,61],"recordings.":[44],"propose":[46],"deep":[48],"neural":[49],"network":[50,107,126,153],"(DNN)":[51],"architecture,":[52],"that":[53,151],"predicts":[54,64],"count":[57,72],"zero":[59],"for":[60,73,170],"recordings":[62,90,138,144],"individual":[66],"clean":[67],"signals":[69],"The":[80,106,125],"DNN":[81],"is":[82,127],"composed":[83,134],"transformer":[85],"layers":[86],"processes":[88],"using":[91],"long-time":[93],"short-time":[95],"sequence":[96],"modeling":[97],"approach":[98],"masking":[100],"learned":[103],"time-feature":[104],"domain.":[105],"uses":[108],"an":[109],"encoder-decoder":[110],"attractor":[111],"module":[112],"long-short":[114],"term":[115],"memory":[116],"units":[117],"generate":[119],"variable":[121],"number":[122],"outputs.":[124],"trained":[128],"simulated":[130],"WSJ0":[140],"corpus,":[141],"noise":[143],"WHAM!":[147],"corpus.":[148],"show":[150],"achieves":[154],"99%":[155],"accuracy":[158],"more":[160],"than":[161],"19":[162],"dB":[163],"improvement":[164],"scale-invariant":[167],"signal-to-noise":[168],"ratio":[169],"up":[173],"three":[175]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}