{"id":"https://openalex.org/W4205139742","doi":"https://doi.org/10.23919/eusipco54536.2021.9616282","title":"Speaker-Aware Speech Enhancement with Self-Attention","display_name":"Speaker-Aware Speech Enhancement with Self-Attention","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W4205139742","doi":"https://doi.org/10.23919/eusipco54536.2021.9616282"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616282","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616282","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/A5084847368","display_name":"Ju Lin","orcid":"https://orcid.org/0000-0002-6970-4247"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ju Lin","raw_affiliation_strings":["Clemson University, Clemson, SC"],"affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, SC","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070024925","display_name":"A. van Wijngaarden","orcid":"https://orcid.org/0000-0002-7394-5326"},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adriaan J. Van Wijngaarden","raw_affiliation_strings":["Nokia Bell Labs, Murray Hill, NJ"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Murray Hill, NJ","institution_ids":["https://openalex.org/I72090969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043923029","display_name":"Melissa C. Smith","orcid":"https://orcid.org/0000-0003-0798-8536"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Melissa C. Smith","raw_affiliation_strings":["Clemson University, Clemson, SC"],"affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, SC","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013311813","display_name":"Kuang\u2010Ching Wang","orcid":"https://orcid.org/0000-0002-5675-7104"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kuang-Ching Wang","raw_affiliation_strings":["Clemson University, Clemson, SC"],"affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, SC","institution_ids":["https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084847368"],"corresponding_institution_ids":["https://openalex.org/I8078737"],"apc_list":null,"apc_paid":null,"fwci":1.7204,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.91202149,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"486","last_page":"490"},"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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":0.9976000189781189,"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":0.8469987511634827},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.8069018125534058},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7890585064888},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7048563957214355},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5111322999000549},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5057148933410645},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46531417965888977},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.46016594767570496},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4331139624118805},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3686560392379761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3601230978965759},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2732182741165161}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8469987511634827},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8069018125534058},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7890585064888},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7048563957214355},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5111322999000549},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5057148933410645},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46531417965888977},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.46016594767570496},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4331139624118805},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3686560392379761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3601230978965759},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2732182741165161},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616282","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616282","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":[],"awards":[{"id":"https://openalex.org/G5028899272","display_name":null,"funder_award_id":"W81XWH-17-C-0238","funder_id":"https://openalex.org/F4320338280","funder_display_name":"Medical Research and Materiel Command"}],"funders":[{"id":"https://openalex.org/F4320338280","display_name":"Medical Research and Materiel Command","ror":"https://ror.org/03cd02q50"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1836465849","https://openalex.org/W1983108229","https://openalex.org/W2044893557","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2187089797","https://openalex.org/W2290318471","https://openalex.org/W2405774341","https://openalex.org/W2603567530","https://openalex.org/W2788241093","https://openalex.org/W2808631503","https://openalex.org/W2889442120","https://openalex.org/W2940177920","https://openalex.org/W2949558265","https://openalex.org/W2951130829","https://openalex.org/W2962788625","https://openalex.org/W2963285578","https://openalex.org/W2963341071","https://openalex.org/W2964058413","https://openalex.org/W2972542211","https://openalex.org/W2973016613","https://openalex.org/W2973062255","https://openalex.org/W2973096665","https://openalex.org/W2998678989","https://openalex.org/W3015219411","https://openalex.org/W3015306128","https://openalex.org/W3016129867","https://openalex.org/W3026111682","https://openalex.org/W3094932283","https://openalex.org/W3096214032","https://openalex.org/W3096641561","https://openalex.org/W3096964161","https://openalex.org/W3134695619","https://openalex.org/W3211408542","https://openalex.org/W4253928870","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6685562342","https://openalex.org/W6739901393","https://openalex.org/W6762114000"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,25],"aims":[2],"to":[3,47,76],"improve":[4],"the":[5,49,72],"intelligibility":[6],"and":[7,38,81],"quality":[8],"of":[9,59,67,87],"speech":[10,24],"that":[11,28,62],"is":[12,54],"affected":[13],"by":[14],"noise.":[15],"In":[16],"this":[17],"paper,":[18],"we":[19],"propose":[20],"a":[21,41,57,64,88],"novel":[22],"speaker-aware":[23],"(SASE)":[26],"method":[27,75],"extracts":[29],"speaker":[30,51],"information":[31],"using":[32],"long":[33],"short-term":[34],"memory":[35],"(LSTM)":[36],"layers,":[37],"then":[39],"uses":[40],"convolutional":[42],"recurrent":[43],"neural":[44],"network":[45],"(CRN)":[46],"embed":[48],"extracted":[50],"information.":[52],"It":[53],"shown":[55],"in":[56],"series":[58],"comprehensive":[60],"experiments":[61],"only":[63],"few":[65],"seconds":[66],"reference":[68],"audio":[69],"suffice":[70],"for":[71],"proposed":[73],"SASE":[74],"perform":[77],"better":[78],"than":[79],"LSTM":[80],"CRN":[82],"baseline":[83],"systems.":[84],"The":[85],"addition":[86],"self-attention":[89],"mechanism":[90],"can":[91],"further":[92],"boost":[93],"relevant":[94],"speech-quality":[95],"metrics.":[96]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}