{"id":"https://openalex.org/W3148386121","doi":"https://doi.org/10.1109/slt48900.2021.9383539","title":"Multimodal Attention Fusion for Target Speaker Extraction","display_name":"Multimodal Attention Fusion for Target Speaker Extraction","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3148386121","doi":"https://doi.org/10.1109/slt48900.2021.9383539","mag":"3148386121"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383539","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5049917170","display_name":"Hiroshi Sat\u014d","orcid":"https://orcid.org/0000-0002-5899-1340"},"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":"Hiroshi Sato","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070624983","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-2519-2032"},"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":"Tsubasa Ochiai","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","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":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","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 Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","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 Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","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 Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"778","last_page":"784"},"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":0.9995999932289124,"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":0.9987000226974487,"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":0.8374481797218323},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7143945693969727},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.552650511264801},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5429638624191284},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5109726190567017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5017716884613037},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4517001509666443},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.44235724210739136},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.442344069480896},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4295770525932312},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4137868881225586},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33725640177726746},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.10172286629676819},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.07169923186302185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8374481797218323},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7143945693969727},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.552650511264801},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5429638624191284},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5109726190567017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5017716884613037},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4517001509666443},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.44235724210739136},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.442344069480896},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4295770525932312},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4137868881225586},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33725640177726746},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.10172286629676819},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.07169923186302185},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"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/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383539","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2096733369","https://openalex.org/W2127851351","https://openalex.org/W2133564696","https://openalex.org/W2221409856","https://openalex.org/W2734774145","https://openalex.org/W2749510669","https://openalex.org/W2891833136","https://openalex.org/W2939771864","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2963082324","https://openalex.org/W2964121744","https://openalex.org/W2964171275","https://openalex.org/W2964238697","https://openalex.org/W2964308564","https://openalex.org/W2972513594","https://openalex.org/W2972568703","https://openalex.org/W3008400075","https://openalex.org/W3011424113","https://openalex.org/W3015636705","https://openalex.org/W3099206234","https://openalex.org/W3099330747","https://openalex.org/W4289665794","https://openalex.org/W6631190155","https://openalex.org/W6679434410"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Target":[0],"speaker":[1,30,49,189],"extraction,":[2],"which":[3],"aims":[4],"at":[5],"extracting":[6],"a":[7,12,52,124],"target":[8,29,37,48,188],"speaker's":[9],"voice":[10],"from":[11],"mixture":[13],"of":[14,82,142,176],"voices":[15],"using":[16,40],"audio,":[17],"visual":[18,44,112,181],"or":[19],"locational":[20],"clues,":[21],"has":[22,32,68],"received":[23],"much":[24],"interest.":[25],"Recently":[26],"an":[27,173],"audio-visual":[28,47,174,187],"extraction":[31,50,190],"been":[33,70],"proposed":[34],"that":[35,135,186],"extracts":[36],"speech":[38,178],"by":[39,117,159],"complementary":[41],"audio":[42],"and":[43,131,145,184],"clues.":[45],"Although":[46],"offers":[51],"more":[53,148],"stable":[54],"performance":[55],"than":[56],"single":[57],"modality":[58],"methods":[59,134],"for":[60,128],"simulated":[61,167],"data,":[62],"its":[63,132],"adaptation":[64],"towards":[65],"realistic":[66,88,180],"situations":[67,89],"not":[69,107],"fully":[71],"explored":[72],"as":[73,75],"well":[74],"evaluations":[76],"on":[77,166,196],"real":[78,102,197],"recorded":[79],"mixtures.":[80],"One":[81],"the":[83,94,140,143,147],"major":[84],"issues":[85],"to":[86,92,97,137,155],"handle":[87],"is":[90],"how":[91],"make":[93],"system":[95],"robust":[96],"clue":[98,182],"corruption":[99,183],"because":[100],"in":[101],"recordings":[103],"both":[104],"clues":[105,113,144],"may":[106,114],"be":[108,115],"equally":[109],"reliable,":[110],"e.g.":[111],"affected":[116],"occlusions.":[118],"In":[119],"this":[120],"work,":[121],"we":[122,170],"propose":[123],"novel":[125],"attention":[126],"mechanism":[127],"multi-modal":[129],"fusion":[130,164],"training":[133],"enable":[136],"effectively":[138],"capture":[139],"reliability":[141],"weight":[146],"reliable":[149],"ones.":[150],"Our":[151],"proposals":[152,193],"improve":[153],"signal":[154],"distortion":[156],"ratio":[157],"(SDR)":[158],"1.0":[160],"dB":[161],"over":[162],"conventional":[163],"mechanisms":[165],"data.":[168,198],"Moreover,":[169],"also":[171],"record":[172],"dataset":[175],"simultaneous":[177],"with":[179,191],"show":[185],"our":[192],"successfully":[194],"work":[195]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}