{"id":"https://openalex.org/W2773082988","doi":"https://doi.org/10.1109/icassp.2018.8462159","title":"Classification vs. Regression in Supervised Learning for Single Channel Speaker Count Estimation","display_name":"Classification vs. Regression in Supervised Learning for Single Channel Speaker Count Estimation","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2773082988","doi":"https://doi.org/10.1109/icassp.2018.8462159","mag":"2773082988"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1712.04555","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051066378","display_name":"Fabian-Robert St\u00f6ter","orcid":"https://orcid.org/0000-0002-2534-1165"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]},{"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fabian-Robert Stoter","raw_affiliation_strings":["International Audio Laboratories, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Fraunhofer institute for Integrated Circuits (IIS), Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Fraunhofer institute for Integrated Circuits (IIS), Erlangen, Germany","institution_ids":["https://openalex.org/I181369854","https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047247941","display_name":"Soumitro Chakrabarty","orcid":"https://orcid.org/0000-0002-0846-207X"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]},{"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Soumitro Chakrabarty","raw_affiliation_strings":["International Audio Laboratories, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Fraunhofer institute for Integrated Circuits (IIS), Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Fraunhofer institute for Integrated Circuits (IIS), Erlangen, Germany","institution_ids":["https://openalex.org/I181369854","https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022331149","display_name":"Bernd Edler","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]},{"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bernd Edler","raw_affiliation_strings":["International Audio Laboratories, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Fraunhofer institute for Integrated Circuits (IIS), Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Fraunhofer institute for Integrated Circuits (IIS), Erlangen, Germany","institution_ids":["https://openalex.org/I181369854","https://openalex.org/I4210123192"]}]},{"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/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]},{"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Emanuel A. P. Habets","raw_affiliation_strings":["International Audio Laboratories, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Fraunhofer institute for Integrated Circuits (IIS), Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Fraunhofer institute for Integrated Circuits (IIS), Erlangen, Germany","institution_ids":["https://openalex.org/I181369854","https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"436","last_page":"440"},"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":0.9998999834060669,"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":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.7730633020401001},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6432310342788696},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6308203935623169},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6124253273010254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5265607833862305},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5089728832244873},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4636721611022949},{"id":"https://openalex.org/keywords/integer","display_name":"Integer (computer science)","score":0.45984992384910583},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.45090311765670776},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4329669177532196},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38688719272613525},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34869256615638733},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11110454797744751},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08662146329879761}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7730633020401001},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6432310342788696},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6308203935623169},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6124253273010254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5265607833862305},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5089728832244873},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4636721611022949},{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.45984992384910583},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.45090311765670776},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4329669177532196},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38688719272613525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34869256615638733},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11110454797744751},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08662146329879761},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2018.8462159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1712.04555","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.04555","pdf_url":"https://arxiv.org/pdf/1712.04555","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:fraunhofer.de:N-520121","is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-520121.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (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":"Fraunhofer IIS","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/403087","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/403087","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":"conference paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1712.04555","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.04555","pdf_url":"https://arxiv.org/pdf/1712.04555","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W299254312","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1583001605","https://openalex.org/W1594771616","https://openalex.org/W1605972624","https://openalex.org/W1907657117","https://openalex.org/W1909455558","https://openalex.org/W1910776219","https://openalex.org/W1954873805","https://openalex.org/W1978232622","https://openalex.org/W2029880715","https://openalex.org/W2064675550","https://openalex.org/W2069143585","https://openalex.org/W2081045838","https://openalex.org/W2125833791","https://openalex.org/W2143612262","https://openalex.org/W2159591770","https://openalex.org/W2160779631","https://openalex.org/W2171679232","https://openalex.org/W2221409856","https://openalex.org/W2401494929","https://openalex.org/W2460742184","https://openalex.org/W2519965060","https://openalex.org/W2520723410","https://openalex.org/W2526050071","https://openalex.org/W2541389513","https://openalex.org/W2557283755","https://openalex.org/W2560481731","https://openalex.org/W2566935005","https://openalex.org/W2575145750","https://openalex.org/W2626961305","https://openalex.org/W2950826633","https://openalex.org/W2951387960","https://openalex.org/W2962683745","https://openalex.org/W2963686699","https://openalex.org/W2963717945","https://openalex.org/W4250668832","https://openalex.org/W4307164413","https://openalex.org/W6610533790","https://openalex.org/W6629717138","https://openalex.org/W6631190155","https://openalex.org/W6634891727","https://openalex.org/W6635652743","https://openalex.org/W6636473274","https://openalex.org/W6639759915","https://openalex.org/W6681513673","https://openalex.org/W6683749202","https://openalex.org/W6704286313","https://openalex.org/W6712646226","https://openalex.org/W6718827390","https://openalex.org/W6726944409","https://openalex.org/W6727040340","https://openalex.org/W6729211573","https://openalex.org/W6730242942","https://openalex.org/W6731719502","https://openalex.org/W6739192308","https://openalex.org/W6763450304"],"related_works":["https://openalex.org/W2052299349","https://openalex.org/W4297728441","https://openalex.org/W1901944325","https://openalex.org/W2789801754","https://openalex.org/W2187824534","https://openalex.org/W2148720069","https://openalex.org/W2794524342","https://openalex.org/W1976985527","https://openalex.org/W2387965307","https://openalex.org/W2766088533"],"abstract_inverted_index":{"The":[0],"task":[1,144],"of":[2,7,155],"estimating":[3],"the":[4,67,109,138,143],"maximum":[5],"number":[6],"concurrent":[8],"speakers":[9],"from":[10],"single":[11],"channel":[12],"mixtures":[13,154],"is":[14],"important":[15,98],"for":[16,128,142,148],"various":[17],"audio-based":[18],"applications,":[19],"such":[20,107],"as":[21,76,85,108],"blind":[22],"source":[23,73],"separation,":[24],"speaker":[25,49,129],"diarisation,":[26],"audio":[27,117],"surveillance":[28],"or":[29,88],"auditory":[30],"scene":[31],"classification.":[32],"Building":[33],"upon":[34],"powerful":[35],"machine":[36],"learning":[37],"methodology,":[38],"we":[39,95],"develop":[40],"a":[41,48,77,86,89,114,121],"Deep":[42],"Neural":[43],"Network":[44],"(DNN)":[45],"that":[46],"estimates":[47],"count.":[50],"While":[51],"DNNs":[52],"efficiently":[53],"map":[54],"input":[55,110],"representations":[56],"to":[57,64,70,157],"output":[58,69],"targets,":[59],"it":[60],"remains":[61],"unclear":[62],"how":[63],"best":[65,139],"handle":[66],"network":[68,126],"infer":[71],"integer":[72],"count":[74,79,130],"estimates,":[75],"discrete":[78],"estimate":[80],"can":[81],"either":[82],"be":[83],"tackled":[84],"regression":[87],"classification":[90],"problem.":[91],"In":[92],"this":[93,97],"paper,":[94],"investigate":[96],"design":[99],"decision":[100],"and":[101,145],"also":[102],"address":[103],"complementary":[104],"parameter":[105],"choices":[106],"representation.":[111],"We":[112],"evaluate":[113],"state-of-the-art":[115],"DNN":[116],"model":[118],"based":[119],"on":[120],"Bi-directional":[122],"Long":[123],"Short-Term":[124],"Memory":[125],"architecture":[127],"estimations.":[131],"Through":[132],"experimental":[133],"evaluations":[134],"aimed":[135],"at":[136],"identifying":[137],"overall":[140],"strategy":[141],"show":[146],"results":[147],"five":[149],"seconds":[150],"speech":[151],"segments":[152],"in":[153],"up":[156],"ten":[158],"speakers.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2017-12-22T00:00:00"}