{"id":"https://openalex.org/W3008663086","doi":"https://doi.org/10.1109/asru46091.2019.9003962","title":"End-to-End Overlapped Speech Detection and Speaker Counting with Raw Waveform","display_name":"End-to-End Overlapped Speech Detection and Speaker Counting with Raw Waveform","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008663086","doi":"https://doi.org/10.1109/asru46091.2019.9003962","mag":"3008663086"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003962","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5071937621","display_name":"Wangyou Zhang","orcid":"https://orcid.org/0000-0003-4500-3515"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangyou Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103897732","display_name":"Man Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Man Sun","raw_affiliation_strings":["Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363653","display_name":"Lan Wang","orcid":"https://orcid.org/0000-0002-7341-4904"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lan Wang","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"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":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"660","last_page":"666"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.8148748278617859},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6993677020072937},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6104838848114014},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.610036313533783},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6062922477722168},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.600312352180481},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5098161101341248},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.492306113243103},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48422789573669434},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4798707067966461},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.471030056476593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4088697135448456},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07300645112991333},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07136967778205872}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148748278617859},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6993677020072937},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6104838848114014},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.610036313533783},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6062922477722168},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.600312352180481},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5098161101341248},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.492306113243103},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48422789573669434},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4798707067966461},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.471030056476593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4088697135448456},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07300645112991333},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07136967778205872},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003962","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1836465849","https://openalex.org/W1991139021","https://openalex.org/W2047527596","https://openalex.org/W2098441927","https://openalex.org/W2099333848","https://openalex.org/W2169264834","https://openalex.org/W2193413348","https://openalex.org/W2296073425","https://openalex.org/W2400757468","https://openalex.org/W2401567014","https://openalex.org/W2772736377","https://openalex.org/W2773082988","https://openalex.org/W2797412426","https://openalex.org/W2810934215","https://openalex.org/W2889381673","https://openalex.org/W2898395910","https://openalex.org/W2949117887","https://openalex.org/W2962696180","https://openalex.org/W3105684258","https://openalex.org/W6687566353","https://openalex.org/W6712682603","https://openalex.org/W6753285601"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2294333436","https://openalex.org/W3110551121","https://openalex.org/W2653598178","https://openalex.org/W2373767407","https://openalex.org/W2131486661","https://openalex.org/W2089240210","https://openalex.org/W642007152","https://openalex.org/W2072884270","https://openalex.org/W4200596008"],"abstract_inverted_index":{"Overlapped":[0],"speech":[1,22,37,66,123,161,194],"processing":[2,19,38],"has":[3],"attracted":[4],"more":[5,7,184],"and":[6,12,68,100,125,187,196],"attention":[8],"in":[9,50,59],"recent":[10],"years,":[11],"it":[13],"is":[14,29,48,56,72,128,143],"a":[15,63,139],"key":[16],"problem":[17],"when":[18],"multi-talker":[20,159],"mixed":[21,160],"under":[23],"the":[24,33,44,98,101,134,150,164,175],"cocktail":[25],"party":[26],"scenario.":[27],"It":[28],"commonly":[30],"observed":[31],"that":[32,170],"performance":[34],"of":[35,46,149],"overlapped":[36,65,122,193],"can":[39,88],"be":[40,89],"significantly":[41],"improved":[42],"if":[43],"number":[45],"speakers":[47],"given":[49],"advance.":[51],"However,":[52],"such":[53],"prior":[54],"knowledge":[55],"often":[57],"unavailable":[58],"real-world":[60],"conditions,":[61],"so":[62],"robust":[64],"detection":[67,124,195],"speaker":[69,126,197],"counting":[70,127,198],"system":[71],"demanded.":[73],"Most":[74],"existing":[75],"works":[76],"focus":[77],"on":[78,158,180,192],"combining":[79],"different":[80],"handcrafted":[81,178],"features":[82,99,132,179],"to":[83,108,145],"tackle":[84],"this":[85,104],"task,":[86],"which":[87,130],"sub-optimal":[90],"since":[91],"there":[92],"are":[93,156],"no":[94],"direct":[95],"connections":[96],"between":[97],"task.":[102],"In":[103],"work,":[105],"we":[106],"try":[107],"solve":[109],"these":[110],"two":[111],"problems":[112],"with":[113,177],"an":[114,118],"end-to-end":[115,119],"manner.":[116],"First,":[117],"framework":[120],"for":[121],"proposed,":[129],"extracts":[131],"from":[133,163],"raw":[135],"waveform":[136],"directly.":[137],"Then":[138],"curriculum":[140],"learning":[141],"strategy":[142],"applied":[144],"make":[146],"better":[147],"use":[148],"training":[151],"data.":[152],"The":[153],"proposed":[154,172],"methods":[155,173],"evaluated":[157],"generated":[162],"LibriSpeech":[165],"corpus.":[166],"Experimental":[167],"results":[168],"show":[169],"our":[171],"outperform":[174],"model":[176],"both":[181],"tasks,":[182],"achieving":[183],"than":[185],"2%":[186],"4%":[188],"absolute":[189],"accuracy":[190],"improvement":[191],"respectively.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}