{"id":"https://openalex.org/W3196705474","doi":"https://doi.org/10.21437/interspeech.2021-331","title":"Real-Time Speaker Counting in a Cocktail Party Scenario Using Attention-Guided Convolutional Neural Network","display_name":"Real-Time Speaker Counting in a Cocktail Party Scenario Using Attention-Guided Convolutional Neural Network","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196705474","doi":"https://doi.org/10.21437/interspeech.2021-331","mag":"3196705474"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-331","doi":"https://doi.org/10.21437/interspeech.2021-331","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-331","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"Interspeech 2021","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.00316","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112853229","display_name":"Midia Yousefi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Midia Yousefi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8086,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.75009788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1484","last_page":"1488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7749000191688538,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7749000191688538,"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/T10860","display_name":"Speech and Audio Processing","score":0.22030000388622284,"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":0.003000000026077032,"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/overlapping-speech","display_name":"overlapping speech","score":0.8460000157356262},{"id":"https://openalex.org/keywords/cocktail-party-problem","display_name":"cocktail party problem","score":0.9399999976158142},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.8889999985694885},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.8920000195503235},{"id":"https://openalex.org/keywords/real-time-speech-processing","display_name":"real-time speech processing","score":0.6470000147819519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8123893141746521},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7607065439224243},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7299542427062988},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6877872943878174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5223641991615295},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.478508859872818},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4726860821247101},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45574191212654114},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4467657804489136},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.42867526412010193},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4163312315940857},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-331","doi":"https://doi.org/10.21437/interspeech.2021-331","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-331","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2111.00316","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.00316","pdf_url":"https://arxiv.org/pdf/2111.00316","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3210508785","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2111.00316","pdf_url":null,"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,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2111.00316","doi":"https://doi.org/10.48550/arxiv.2111.00316","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2111.00316","pdf_url":null,"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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2111.00316","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.00316","pdf_url":"https://arxiv.org/pdf/2111.00316","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3196705474.pdf","grobid_xml":"https://content.openalex.org/works/W3196705474.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2962696180","https://openalex.org/W4315836142","https://openalex.org/W3012169242","https://openalex.org/W2898395910","https://openalex.org/W2907228390","https://openalex.org/W3120137480","https://openalex.org/W4392903939","https://openalex.org/W3038713101","https://openalex.org/W4404577251","https://openalex.org/W4388623407"],"abstract_inverted_index":{"Most":[0],"current":[1],"speech":[2,72,111,152],"technology":[3],"systems":[4],"are":[5,100],"designed":[6],"to":[7,54,122],"operate":[8],"well":[9],"even":[10],"in":[11,38,61,172],"the":[12,23,56,71,80,84,97,117,124,163,169,176],"presence":[13],"of":[14,25,58],"multiple":[15],"active":[16,59,98],"speakers.":[17],"However,":[18],"most":[19],"solutions":[20],"assume":[21],"that":[22,116],"number":[24,57],"co-current":[26],"speakers":[27,60,99],"is":[28,120,179],"known.":[29],"Unfortunately,":[30],"this":[31,42],"information":[32,69,86],"might":[33],"not":[34],"always":[35],"be":[36],"available":[37],"real-world":[39],"applications.":[40],"In":[41],"study,":[43],"we":[44],"propose":[45],"a":[46,76,88,103],"real-time,":[47],"single-channel":[48],"attention-guided":[49,170],"Convolutional":[50],"Neural":[51],"Network":[52],"(CNN)":[53],"estimate":[55],"overlapping":[62,110],"speech.":[63],"The":[64,135],"proposed":[65,136],"system":[66],"extracts":[67],"higher-level":[68],"from":[70],"spectral":[73],"content":[74],"using":[75,102,112],"CNN":[77,138],"model.":[78],"Next,":[79],"attention":[81,118],"mechanism":[82],"summarizes":[83],"extracted":[85],"into":[87],"compact":[89],"feature":[90],"vector":[91],"without":[92],"losing":[93],"critical":[94],"information.":[95],"Finally,":[96],"classified":[101],"fully":[104],"connected":[105],"network.":[106],"Experiments":[107],"on":[108,151],"simulated":[109],"WSJ":[113],"corpus":[114],"show":[115],"solution":[119],"shown":[121],"improve":[123],"performance":[125],"by":[126],"almost":[127],"3%":[128],"absolute":[129],"over":[130],"conventional":[131],"temporal":[132],"average":[133,146],"pooling.":[134],"Attention-guided":[137],"achieves":[139],"76.15%":[140],"for":[141,168],"both":[142],"Weighted":[143],"Accuracy":[144],"and":[145,148],"Recall,":[147],"75.80%":[149],"Precision":[150],"segments":[153],"as":[154,156],"short":[155],"20":[157],"frames":[158,183],"(i.e.,":[159,185],"200":[160],"ms).":[161],"All":[162],"classification":[164],"metrics":[165],"exceed":[166],"92%":[167],"model":[171],"offline":[173],"scenarios":[174],"where":[175],"input":[177],"signal":[178],"more":[180],"than":[181],"100":[182],"long":[184],"1s).":[186]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-09-13T00:00:00"}