{"id":"https://openalex.org/W3016244460","doi":"https://doi.org/10.1109/icassp40776.2020.9054577","title":"Tackling Real Noisy Reverberant Meetings with All-Neural Source Separation, Counting, and Diarization System","display_name":"Tackling Real Noisy Reverberant Meetings with All-Neural Source Separation, Counting, and Diarization System","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016244460","doi":"https://doi.org/10.1109/icassp40776.2020.9054577","mag":"3016244460"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054577","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":"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/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Communication Science Labs, NTT corporation"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Labs, NTT corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Labs, NTT corporation"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Labs, NTT corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Communication Science Labs, NTT corporation"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Labs, NTT corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Labs, NTT corporation"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Labs, NTT corporation","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069398831"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":4.546,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.95510204,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"381","last_page":"385"},"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":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8122944831848145},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7857087850570679},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6609342694282532},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6457176804542542},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5893568396568298},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5646785497665405},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.5388479232788086},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5155805945396423},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.47848862409591675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4407534599304199},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08338087797164917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8122944831848145},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7857087850570679},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6609342694282532},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6457176804542542},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5893568396568298},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5646785497665405},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.5388479232788086},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5155805945396423},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.47848862409591675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4407534599304199},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08338087797164917},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054577","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2005733316","https://openalex.org/W2081074144","https://openalex.org/W2125336414","https://openalex.org/W2127851351","https://openalex.org/W2141398670","https://openalex.org/W2150769028","https://openalex.org/W2159284737","https://openalex.org/W2221409856","https://openalex.org/W2325237720","https://openalex.org/W2460742184","https://openalex.org/W2587150483","https://openalex.org/W2606300880","https://openalex.org/W2612434969","https://openalex.org/W2734774145","https://openalex.org/W2803322398","https://openalex.org/W2889381673","https://openalex.org/W2889418727","https://openalex.org/W2889755093","https://openalex.org/W2891054259","https://openalex.org/W2952218014","https://openalex.org/W2952752702","https://openalex.org/W2972767900","https://openalex.org/W2972949456","https://openalex.org/W3015636705","https://openalex.org/W3099330747","https://openalex.org/W3208240190","https://openalex.org/W6701498492","https://openalex.org/W6733275487","https://openalex.org/W6737575990","https://openalex.org/W6773173422"],"related_works":["https://openalex.org/W2098987383","https://openalex.org/W2417260800","https://openalex.org/W1596203174","https://openalex.org/W2117933979","https://openalex.org/W3210882018","https://openalex.org/W2970990331","https://openalex.org/W4379116102","https://openalex.org/W3207178610","https://openalex.org/W3211782752","https://openalex.org/W4309864825"],"abstract_inverted_index":{"Automatic":[0],"meeting":[1,25,107,155],"analysis":[2],"is":[3],"an":[4,22,30,45],"essential":[5],"fundamental":[6],"technology":[7],"required":[8,138],"to":[9,17,103],"let,":[10],"e.g.":[11],"smart":[12],"devices":[13],"follow":[14],"and":[15,40,75,79,115,117,147,165],"respond":[16],"our":[18],"conversations.":[19],"To":[20],"achieve":[21],"optimal":[23,46],"automatic":[24],"analysis,":[26],"we":[27,133],"previously":[28],"proposed":[29],"all-neural":[31,97,145,158],"approach":[32,98,159],"that":[33,51,66],"jointly":[34,58],"solves":[35],"source":[36,41],"separation,":[37],"speaker":[38],"diarization":[39],"counting":[42],"problems":[43],"in":[44,84,121,127,153],"way":[47],"(in":[48],"a":[49],"sense":[50],"all":[52],"the":[53,67,124,141,144,157],"3":[54],"tasks":[55],"can":[56,160],"be":[57,100],"optimized":[59],"through":[60],"error":[61],"back-propagation).":[62],"It":[63],"was":[64,92],"shown":[65],"method":[68],"could":[69],"well":[70],"handle":[71],"simulated":[72],"clean":[73],"(noiseless":[74],"anechoic)":[76],"dialog-like":[77],"data,":[78],"achieved":[80],"very":[81],"good":[82],"performance":[83],"comparison":[85,122],"with":[86,123],"several":[87],"conventional":[88],"methods.":[89],"However,":[90],"it":[91,119],"not":[93],"clear":[94],"whether":[95],"such":[96,128],"would":[99],"successfully":[101],"generalized":[102],"more":[104,110],"complicated":[105],"real":[106,154],"data":[108],"containing":[109],"spontaneously-speaking":[111],"speakers,":[112],"severe":[113],"noise":[114],"reverberation,":[116],"how":[118],"performs":[120],"state-of-the-art":[125,168],"systems":[126],"scenarios.":[129],"In":[130],"this":[131],"paper,":[132],"first":[134],"consider":[135],"practical":[136],"issues":[137],"for":[139],"improving":[140],"robustness":[142],"of":[143],"approach,":[146],"then":[148],"experimentally":[149],"show":[150],"that,":[151],"even":[152],"scenarios,":[156],"perform":[161],"effective":[162],"speech":[163],"enhancement,":[164],"simultaneously":[166],"outperform":[167],"systems.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}