{"id":"https://openalex.org/W3015810999","doi":"https://doi.org/10.1109/icassp40776.2020.9053317","title":"Progressive Multi-Target Network Based Speech Enhancement with Snr-Preselection for Robust Speaker Diarization","display_name":"Progressive Multi-Target Network Based Speech Enhancement with Snr-Preselection for Robust Speaker Diarization","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015810999","doi":"https://doi.org/10.1109/icassp40776.2020.9053317","mag":"3015810999"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101926390","display_name":"Lei Sun","orcid":"https://orcid.org/0000-0001-7680-6455"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Sun","raw_affiliation_strings":["University of Science and Technology of China, Hefei, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China, Hefei, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101428754","display_name":"Xueyang Zhang","orcid":"https://orcid.org/0000-0002-6428-0414"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xueyang Zhang","raw_affiliation_strings":["iFlytek Research, Hefei, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek Research, Hefei, P. R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101590046","display_name":"Tian Gao","orcid":"https://orcid.org/0000-0002-9523-5560"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Gao","raw_affiliation_strings":["iFlytek Research, Hefei, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek Research, Hefei, P. R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101716884","display_name":"Xin Fang","orcid":"https://orcid.org/0000-0003-4796-9444"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Fang","raw_affiliation_strings":["iFlytek Research, Hefei, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek Research, Hefei, P. R. China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7099","last_page":"7103"},"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":0.9998999834060669,"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":0.9990000128746033,"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":0.8115934729576111},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7665804624557495},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7493509650230408},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6153630614280701},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5362078547477722},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5326962471008301},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5159328579902649},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4809252917766571},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4794289469718933},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.47147229313850403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46063458919525146},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4548524022102356},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.43967145681381226},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4318453073501587},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42108774185180664},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3694959282875061},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2456013262271881},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09733814001083374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115934729576111},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7665804624557495},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7493509650230408},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6153630614280701},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5362078547477722},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5326962471008301},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5159328579902649},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4809252917766571},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4794289469718933},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.47147229313850403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46063458919525146},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4548524022102356},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.43967145681381226},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4318453073501587},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42108774185180664},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3694959282875061},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2456013262271881},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09733814001083374},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W118310762","https://openalex.org/W1494198834","https://openalex.org/W1607302042","https://openalex.org/W1608667326","https://openalex.org/W1995593724","https://openalex.org/W2024490156","https://openalex.org/W2035576074","https://openalex.org/W2078528584","https://openalex.org/W2081074144","https://openalex.org/W2098726438","https://openalex.org/W2121812409","https://openalex.org/W2141411743","https://openalex.org/W2150769028","https://openalex.org/W2168175751","https://openalex.org/W2168379380","https://openalex.org/W2219249508","https://openalex.org/W2284628133","https://openalex.org/W2338994564","https://openalex.org/W2516547830","https://openalex.org/W2605589342","https://openalex.org/W2726515241","https://openalex.org/W2802905931","https://openalex.org/W2808631503","https://openalex.org/W2889031312","https://openalex.org/W2889381673","https://openalex.org/W2889418727","https://openalex.org/W2963242190","https://openalex.org/W2963446712","https://openalex.org/W2972449503","https://openalex.org/W2989863749","https://openalex.org/W3208240190","https://openalex.org/W4285719527","https://openalex.org/W6604723554","https://openalex.org/W6636060366","https://openalex.org/W6688816777","https://openalex.org/W6725739302","https://openalex.org/W6802591457"],"related_works":["https://openalex.org/W2059891707","https://openalex.org/W3087422378","https://openalex.org/W2020970176","https://openalex.org/W3120512183","https://openalex.org/W2111874347","https://openalex.org/W2485008119","https://openalex.org/W2978471304","https://openalex.org/W2044038981","https://openalex.org/W4230130602","https://openalex.org/W2948312300"],"abstract_inverted_index":{"In":[0,116],"this":[1],"paper,":[2],"we":[3,25],"design":[4],"a":[5,95,118],"novel":[6],"front-end":[7,77],"processing":[8],"system":[9],"for":[10,106,112],"speaker":[11,114,148],"diarization":[12],"under":[13],"realistic":[14,160],"conditions":[15],"with":[16,22,65,99,163],"challenging":[17],"background":[18],"noises.":[19],"To":[20],"cope":[21],"diversified":[23],"environments,":[24],"first":[26],"extend":[27],"our":[28,175],"perviously":[29],"proposed":[30,87,176],"progressive":[31,47,55],"learning":[32,40,101],"based":[33,132],"speech":[34,88,133],"enhancement":[35,89],"model":[36,90],"by":[37,174],"adding":[38],"multi-task":[39],"in":[41,50,192],"each":[42],"intermediate":[43],"layer.":[44],"The":[45],"corresponding":[46],"multi-target":[48],"(PMT)":[49],"various":[51],"layers":[52],"includes":[53,157],"both":[54],"ratio":[56],"mask":[57],"(PRM)":[58],"and":[59,188],"progressively":[60],"enhanced":[61,171],"log-power":[62],"spectra":[63],"(PELPS)":[64],"specified":[66],"signal-to-noise":[67],"ratios":[68],"(SNRs).":[69],"Speech":[70],"distortions":[71],"are":[72],"commonly":[73],"introduced":[74],"during":[75],"the":[76,82,86,108,125,140,147,152,164,170,181],"processing,":[78],"which":[79,103,156],"often":[80],"deteriorate":[81],"back-end":[83],"performance.":[84],"However,":[85],"can":[91,178],"be":[92,143],"regarded":[93],"as":[94],"bagging":[96],"of":[97,127,184],"models":[98],"multiple":[100],"objectives,":[102],"provides":[104],"flexibility":[105],"selecting":[107],"most":[109,193],"appropriate":[110],"output":[111],"robust":[113],"diarzation.":[115],"addition,":[117],"global":[119],"SNR":[120],"estimation":[121],"is":[122],"performed":[123],"using":[124],"results":[126],"deep":[128],"neural":[129],"network":[130],"(DNN)":[131],"activity":[134],"detection":[135],"(SAD)":[136],"to":[137],"decide":[138],"whether":[139],"audio":[141],"should":[142],"enhanced.":[144],"We":[145],"evaluate":[146],"diarzation":[149],"performance":[150,182],"on":[151],"second":[153],"DIHARD":[154],"dataset":[155],"several":[158],"different":[159],"conditions.":[161],"Compared":[162],"original":[165],"data,":[166],"experiments":[167],"demonstrate":[168],"that":[169],"data":[172],"processed":[173],"method":[177],"effectively":[179],"avoid":[180],"loss":[183],"every":[185],"single":[186],"domain,":[187],"achieve":[189],"consistent":[190],"improvements":[191],"domains.":[194]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}