{"id":"https://openalex.org/W4372270324","doi":"https://doi.org/10.1109/icassp49357.2023.10096732","title":"Dual-Path Cross-Modal Attention for Better Audio-Visual Speech Extraction","display_name":"Dual-Path Cross-Modal Attention for Better Audio-Visual Speech Extraction","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372270324","doi":"https://doi.org/10.1109/icassp49357.2023.10096732"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5069215134","display_name":"Zhongweiyang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhongweiyang Xu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086248084","display_name":"Xulin Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xulin Fan","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069215134"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.4066,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54109032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9998000264167786,"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":0.9970999956130981,"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":0.8283671140670776},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.716249406337738},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6422563195228577},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5463720560073853},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.527912437915802},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46464797854423523},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4131661355495453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3628188371658325}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8283671140670776},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.716249406337738},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6422563195228577},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5463720560073853},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.527912437915802},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46464797854423523},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4131661355495453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3628188371658325},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":46,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2096733369","https://openalex.org/W2341528187","https://openalex.org/W2551572271","https://openalex.org/W2585824449","https://openalex.org/W2734774145","https://openalex.org/W2889624961","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2952218014","https://openalex.org/W2963082324","https://openalex.org/W2964058413","https://openalex.org/W2964171275","https://openalex.org/W2964352155","https://openalex.org/W2972513594","https://openalex.org/W2987346570","https://openalex.org/W3006974783","https://openalex.org/W3008400075","https://openalex.org/W3015199127","https://openalex.org/W3027008958","https://openalex.org/W3035268204","https://openalex.org/W3035626590","https://openalex.org/W3088950396","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3101998545","https://openalex.org/W3148386121","https://openalex.org/W3162293946","https://openalex.org/W3163652268","https://openalex.org/W3174906557","https://openalex.org/W3197669134","https://openalex.org/W4221153068","https://openalex.org/W4289665794","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6746173266","https://openalex.org/W6754079011","https://openalex.org/W6754420807","https://openalex.org/W6774995033","https://openalex.org/W6777776875","https://openalex.org/W6797613833","https://openalex.org/W6810168380"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W4387678054","https://openalex.org/W3000097931","https://openalex.org/W3095575180","https://openalex.org/W2389596151","https://openalex.org/W4221148444","https://openalex.org/W2354322770","https://openalex.org/W4226054107","https://openalex.org/W4306784355","https://openalex.org/W4237547500"],"abstract_inverted_index":{"Audiovisual":[0],"target":[1],"speaker":[2,14],"extraction":[3],"is":[4,17,60,70],"the":[5,13,27,31,35,56,63,88,118,133,139],"task":[6],"of":[7,65,85,141],"separating,":[8],"from":[9,117],"an":[10,20],"audio":[11,57,89],"mixture,":[12],"whose":[15],"face":[16],"visible":[18],"in":[19,54],"accompanying":[21],"video.":[22],"Published":[23],"approaches":[24],"typically":[25],"upsample":[26],"video":[28,67,77,91],"or":[29,41,130],"downsample":[30],"audio,":[32],"then":[33,79],"fuse":[34],"two":[36],"streams":[37],"using":[38],"concatenation,":[39],"multiplication,":[40],"cross-modal":[42],"attention.":[43,83],"This":[44],"paper":[45],"proposes,":[46],"instead,":[47],"to":[48,62,76],"use":[49],"a":[50,66],"dual-path":[51,101],"attention":[52],"architecture":[53],"which":[55],"chunk":[58],"length":[59],"comparable":[61],"duration":[64],"frame.":[68],"Audio":[69],"transformed":[71,80],"by":[72,81],"intra-chunk":[73],"attention,":[74],"concatenated":[75],"features,":[78],"inter-chunk":[82],"Because":[84],"residual":[86],"connections,":[87],"and":[90],"features":[92],"remain":[93],"logically":[94],"distinct":[95],"across":[96,109],"multiple":[97,110],"network":[98],"layers,":[99],"therefore":[100],"audiovisual":[102],"feature":[103],"fusion":[104],"can":[105],"be":[106],"performed":[107],"repeatedly":[108],"layers.":[111],"When":[112],"given":[113],"2-5-speaker":[114],"mixtures":[115],"constructed":[116],"challenging":[119],"LRS3":[120],"test":[121],"set,":[122],"results":[123],"are":[124],"about":[125],"7dB":[126],"better":[127],"than":[128],"Con-vTasNet":[129],"AV-ConvTasNet,":[131],"with":[132],"performance":[134],"gap":[135],"widening":[136],"slightly":[137],"as":[138],"number":[140],"speakers":[142],"increases.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}