{"id":"https://openalex.org/W3015219411","doi":"https://doi.org/10.1109/icassp40776.2020.9053214","title":"Speech Enhancement Using Self-Adaptation and Multi-Head Self-Attention","display_name":"Speech Enhancement Using Self-Adaptation and Multi-Head Self-Attention","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015219411","doi":"https://doi.org/10.1109/icassp40776.2020.9053214","mag":"3015219411"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053214","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/A5101503856","display_name":"Yuma Koizumi","orcid":"https://orcid.org/0000-0003-3645-6213"},"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":"Yuma Koizumi","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034837951","display_name":"Kohei Yatabe","orcid":"https://orcid.org/0000-0002-1345-0663"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kohei Yatabe","raw_affiliation_strings":["Department of Intermedia Art and Science, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intermedia Art and Science, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"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 Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042385500","display_name":"Yoshiki Masuyama","orcid":"https://orcid.org/0000-0002-5881-0474"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiki Masuyama","raw_affiliation_strings":["Department of Intermedia Art and Science, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intermedia Art and Science, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103978078","display_name":"Daiki Takeuchi","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daiki Takeuchi","raw_affiliation_strings":["Department of Intermedia Art and Science, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intermedia Art and Science, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.089,"has_fulltext":false,"cited_by_count":132,"citation_normalized_percentile":{"value":0.99608021,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"181","last_page":"185"},"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":0.9994000196456909,"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":0.9973999857902527,"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":0.8019400835037231},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7889522910118103},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6193804740905762},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5744665861129761},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.561326801776886},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5362510085105896},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4931759238243103},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46581482887268066},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46029648184776306},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4564398229122162},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4528071880340576},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4328632056713104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4113808274269104},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.26332682371139526},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07936406135559082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8019400835037231},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7889522910118103},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6193804740905762},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5744665861129761},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.561326801776886},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5362510085105896},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4931759238243103},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46581482887268066},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46029648184776306},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4564398229122162},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4528071880340576},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4328632056713104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4113808274269104},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.26332682371139526},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07936406135559082},{"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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053214","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":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W2144404214","https://openalex.org/W2221409856","https://openalex.org/W2288645994","https://openalex.org/W2291877678","https://openalex.org/W2502312327","https://openalex.org/W2516559027","https://openalex.org/W2519091744","https://openalex.org/W2603567530","https://openalex.org/W2605320104","https://openalex.org/W2696558042","https://openalex.org/W2734774145","https://openalex.org/W2787685498","https://openalex.org/W2801839390","https://openalex.org/W2802304149","https://openalex.org/W2805233667","https://openalex.org/W2889373351","https://openalex.org/W2891833136","https://openalex.org/W2938646939","https://openalex.org/W2943895317","https://openalex.org/W2949382160","https://openalex.org/W2949558265","https://openalex.org/W2951130829","https://openalex.org/W2962866211","https://openalex.org/W2962923973","https://openalex.org/W2963217176","https://openalex.org/W2963341071","https://openalex.org/W2963403868","https://openalex.org/W2963490782","https://openalex.org/W2964058413","https://openalex.org/W2972443522","https://openalex.org/W2972818416","https://openalex.org/W3007328579","https://openalex.org/W3015360216","https://openalex.org/W3016050488","https://openalex.org/W3103619082","https://openalex.org/W4385245566","https://openalex.org/W6639288305","https://openalex.org/W6724804524","https://openalex.org/W6736204136","https://openalex.org/W6739901393","https://openalex.org/W6762114000","https://openalex.org/W6770459708"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2131486661","https://openalex.org/W2089240210","https://openalex.org/W2161396743","https://openalex.org/W2386453889","https://openalex.org/W3134790285","https://openalex.org/W1565692302"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"a":[3,15,39,70,136],"self-adaptation":[4],"method":[5],"for":[6,19,72,124],"speech":[7,33,45,48,73,96,130],"enhancement":[8,34,74,97],"using":[9],"auxiliary":[10,83,116],"speaker-aware":[11],"features;":[12],"we":[13,91,120],"extract":[14],"speaker":[16,40,61,99,111],"representation":[17],"used":[18],"adaptation":[20,57],"directly":[21],"from":[22],"the":[23,59,63,103,106,129,144],"test":[24],"utterance.":[25],"Conventional":[26],"studies":[27],"of":[28,95,105,110,154],"deep":[29],"neural":[30],"network":[31],"(DNN)-based":[32],"mainly":[35],"focus":[36],"on":[37,135],"building":[38],"independent":[41],"model.":[42],"Meanwhile,":[43],"in":[44,86,128,152],"applications":[46],"including":[47],"recognition":[49],"and":[50,98,101,131,147],"synthesis,":[51],"it":[52],"is":[53,68],"known":[54],"that":[55,140],"model":[56],"to":[58,78],"target":[60],"improves":[62],"accuracy.":[64],"Our":[65],"research":[66],"question":[67],"whether":[69],"DNN":[71],"can":[75],"be":[76],"adopted":[77],"unknown":[79],"speakers":[80],"without":[81],"any":[82],"guidance":[84],"signal":[85],"test-phase.":[87],"To":[88],"achieve":[89],"this,":[90],"adopt":[92],"multi-task":[93],"learning":[94],"identification,":[100],"use":[102,121],"output":[104],"final":[107],"hidden":[108],"layer":[109],"identification":[112],"branch":[113],"as":[114],"an":[115],"feature.":[117],"In":[118],"addition,":[119],"multi-head":[122],"self-attention":[123],"capturing":[125],"long-term":[126],"dependencies":[127],"noise.":[132],"Experimental":[133],"results":[134],"public":[137],"dataset":[138],"show":[139],"our":[141],"strategy":[142],"achieves":[143],"state-of-the-art":[145],"performance":[146],"also":[148],"outperform":[149],"conventional":[150],"methods":[151],"terms":[153],"subjective":[155],"quality.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":46},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}