{"id":"https://openalex.org/W3105483368","doi":"https://doi.org/10.23919/eusipco54536.2021.9616112","title":"Multi-task Single Channel Speech Enhancement Using Speech Presence Probability As A Secondary Task Training Target","display_name":"Multi-task Single Channel Speech Enhancement Using Speech Presence Probability As A Secondary Task Training Target","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3105483368","doi":"https://doi.org/10.23919/eusipco54536.2021.9616112","mag":"3105483368"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616112","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616112","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5101466684","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0002-0050-508X"},"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":true,"raw_author_name":"Lei Wang","raw_affiliation_strings":["Dept. of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Dept. of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036446909","display_name":"Jie Zhu","orcid":"https://orcid.org/0000-0003-2133-4651"},"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":"Jie Zhu","raw_affiliation_strings":["Dept. of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Dept. of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061058558","display_name":"Ina Kodrasi","orcid":"https://orcid.org/0000-0002-1747-1322"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ina Kodrasi","raw_affiliation_strings":["Speech and Audio Processing Group Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Processing Group Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101466684"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.3443,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.49528302,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"296","last_page":"300"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9969000220298767,"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":0.7348595261573792},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6532734036445618},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6379174590110779},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5085028409957886},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5078681111335754},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.48881933093070984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48073720932006836},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4387325942516327},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42588385939598083},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4178411364555359},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.41142237186431885},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3337867259979248},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10464301705360413},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07985147833824158}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7348595261573792},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6532734036445618},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6379174590110779},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5085028409957886},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5078681111335754},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.48881933093070984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48073720932006836},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4387325942516327},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42588385939598083},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4178411364555359},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.41142237186431885},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3337867259979248},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10464301705360413},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07985147833824158},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616112","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616112","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4187866265","display_name":null,"funder_award_id":"6137114","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4668038911","display_name":null,"funder_award_id":"61371147","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1512562331","https://openalex.org/W1603978816","https://openalex.org/W1973669708","https://openalex.org/W1981529844","https://openalex.org/W1983108229","https://openalex.org/W1995190897","https://openalex.org/W2006129368","https://openalex.org/W2040782121","https://openalex.org/W2051428568","https://openalex.org/W2069681747","https://openalex.org/W2077090930","https://openalex.org/W2085191029","https://openalex.org/W2117130368","https://openalex.org/W2121973264","https://openalex.org/W2126288184","https://openalex.org/W2133908567","https://openalex.org/W2144404214","https://openalex.org/W2155889651","https://openalex.org/W2165534711","https://openalex.org/W2542605056","https://openalex.org/W2575485141","https://openalex.org/W2889047169","https://openalex.org/W2913340405","https://openalex.org/W2952979007","https://openalex.org/W2962866211","https://openalex.org/W2963677766","https://openalex.org/W3032514799","https://openalex.org/W3127686677","https://openalex.org/W3147539069","https://openalex.org/W4234149415","https://openalex.org/W6678737727","https://openalex.org/W6680017764","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W2061479026","https://openalex.org/W2810291168","https://openalex.org/W2912659295","https://openalex.org/W3010738343","https://openalex.org/W4224931722","https://openalex.org/W4300661777","https://openalex.org/W1569338400","https://openalex.org/W2110120390","https://openalex.org/W2802812753","https://openalex.org/W2035001151"],"abstract_inverted_index":{"To":[0,124],"cope":[1],"with":[2],"reverberation":[3],"and":[4,23,53,114,117,121,152,203,209],"noise":[5,153,210],"in":[6,74,94,104],"single":[7],"channel":[8],"acoustic":[9],"scenarios,":[10],"typical":[11],"supervised":[12],"deep":[13],"neural":[14],"network":[15],"(DNN)-based":[16],"techniques":[17,78],"learn":[18,126],"a":[19,28,39,62,87,157],"mapping":[20],"from":[21,140],"reverberant":[22],"noisy":[24],"input":[25],"features":[26],"to":[27,60,70,131,161,176,197],"user-defined":[29],"target.":[30],"Commonly":[31],"used":[32,59],"targets":[33],"are":[34],"the":[35,44,48,91,95,109,133,141,150,164,170,178,182,188,192,200,204,207],"desired":[36,179],"signal":[37,180],"magnitude,":[38,181],"time-frequency":[40,63],"mask":[41],"such":[42,75],"as":[43,86],"Wiener":[45,165,201],"gain,":[46],"or":[47,187],"interference":[49,183],"power":[50,184],"spectral":[51,185],"density":[52],"signal-to-interference":[54,189],"ratio":[55],"that":[56,149],"can":[57],"be":[58],"compute":[61],"mask.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68,129],"propose":[69,130],"incorporate":[71],"multi-task":[72,101,194],"learning":[73,102,118,195],"DNN-based":[76],"enhancement":[77],"by":[79],"using":[80],"speech":[81],"presence":[82],"probability":[83],"(SPP)":[84],"estimation":[85,93],"secondary":[88],"task":[89],"assisting":[90],"target":[92,113],"main":[96],"task.":[97],"The":[98],"advantage":[99],"of":[100,137,144,156,172],"lies":[103],"sharing":[105],"domain-specific":[106],"information":[107],"between":[108],"two":[110],"tasks":[111],"(i.e.,":[112],"SPP":[115,205],"estimation)":[116],"more":[119],"generalizable":[120],"robust":[122],"representations.":[123],"simultaneously":[125],"both":[127],"tasks,":[128],"use":[132],"adaptive":[134],"weighting":[135],"method":[136],"losses":[138],"derived":[139],"homoscedastic":[142],"uncertainty":[143],"tasks.":[145],"Simulation":[146],"results":[147],"show":[148],"dereverberation":[151,208],"reduction":[154,211],"performance":[155,171],"single-task":[158,173],"DNN":[159],"trained":[160,175],"directly":[162],"estimate":[163,177,199],"gain":[166,202],"is":[167],"higher":[168],"than":[169],"DNNs":[174],"density,":[186],"ratio.":[190],"Incorporating":[191],"proposed":[193],"scheme":[196],"jointly":[198],"increases":[206],"further.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}