{"id":"https://openalex.org/W4400579920","doi":"https://doi.org/10.1109/jstsp.2024.3427424","title":"A Two-Stage Audio-Visual Speech Separation Method Without Visual Signals for Testing and Tuples Loss With Dynamic Margin","display_name":"A Two-Stage Audio-Visual Speech Separation Method Without Visual Signals for Testing and Tuples Loss With Dynamic Margin","publication_year":2024,"publication_date":"2024-04-01","ids":{"openalex":"https://openalex.org/W4400579920","doi":"https://doi.org/10.1109/jstsp.2024.3427424"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2024.3427424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2024.3427424","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5060046162","display_name":"Yinggang Liu","orcid":"https://orcid.org/0009-0006-7641-616X"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinggang Liu","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0006-7641-616X","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034561537","display_name":"Yuanjie Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanjie Deng","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101478527","display_name":"Ying Wei","orcid":"https://orcid.org/0000-0001-8217-4765"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Wei","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China","School of Control Science and Engineering of Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-8217-4765","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"School of Control Science and Engineering of Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":0.5989,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62645875,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":"18","issue":"3","first_page":"459","last_page":"472"},"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":0.9976999759674072,"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":0.6918046474456787},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6788151264190674},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6716911792755127},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.6516140699386597},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6328148245811462},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4682031273841858},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.46482518315315247},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39826223254203796},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3684026002883911},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18646830320358276},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16801276803016663},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.13812285661697388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6918046474456787},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6788151264190674},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6716911792755127},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.6516140699386597},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6328148245811462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4682031273841858},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.46482518315315247},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39826223254203796},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3684026002883911},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18646830320358276},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16801276803016663},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.13812285661697388},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2024.3427424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2024.3427424","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5144012530","display_name":null,"funder_award_id":"62171263","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2788241093","https://openalex.org/W2808631503","https://openalex.org/W2844030168","https://openalex.org/W2950864153","https://openalex.org/W2952218014","https://openalex.org/W2959214850","https://openalex.org/W2960236182","https://openalex.org/W2962715207","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2963218389","https://openalex.org/W2967735860","https://openalex.org/W2972460025","https://openalex.org/W2973165826","https://openalex.org/W2986592617","https://openalex.org/W2988200020","https://openalex.org/W3000647100","https://openalex.org/W3007589762","https://openalex.org/W3008400075","https://openalex.org/W3010851250","https://openalex.org/W3011424113","https://openalex.org/W3015199127","https://openalex.org/W3015529133","https://openalex.org/W3015915076","https://openalex.org/W3020804303","https://openalex.org/W3090229599","https://openalex.org/W3099330747","https://openalex.org/W3107909154","https://openalex.org/W3118548710","https://openalex.org/W3124972797","https://openalex.org/W3133801870","https://openalex.org/W3136499730","https://openalex.org/W3160244659","https://openalex.org/W3175300676","https://openalex.org/W3176445421","https://openalex.org/W3182657421","https://openalex.org/W4210583256","https://openalex.org/W4214698081","https://openalex.org/W4221107620","https://openalex.org/W4221141685","https://openalex.org/W4226219411","https://openalex.org/W4283837854","https://openalex.org/W4289665794","https://openalex.org/W4291920479","https://openalex.org/W4292337502","https://openalex.org/W4360764593","https://openalex.org/W4372271367","https://openalex.org/W4385756463","https://openalex.org/W6631190155","https://openalex.org/W6786355863","https://openalex.org/W6791353385","https://openalex.org/W6809919126"],"related_works":["https://openalex.org/W4245395944","https://openalex.org/W2143551613","https://openalex.org/W2138823233","https://openalex.org/W1979740464","https://openalex.org/W2143345456","https://openalex.org/W1789991335","https://openalex.org/W2271369634","https://openalex.org/W2562731034","https://openalex.org/W4315705795","https://openalex.org/W2101053337"],"abstract_inverted_index":{"Speech":[0],"separation":[1,22,37,82,101,131,190,212],"as":[2,126,153],"a":[3,42,86,168],"fundamental":[4],"task":[5],"in":[6,12,59,133],"signal":[7],"processing":[8],"can":[9],"be":[10,27],"used":[11,97,152,197],"many":[13],"types":[14],"of":[15,89,129,155],"intelligent":[16],"robots,":[17],"and":[18,122,178,199],"audio-visual":[19],"(AV)":[20],"speech":[21,31,36,81,189,211],"has":[23],"been":[24],"proven":[25],"to":[26,29,56,67,98,144],"superior":[28],"audio-only":[30],"separation.":[32],"In":[33,72],"current":[34,116,209],"AV":[35,80,141,176,188,210],"methods,":[38],"visual":[39,70,90,94,107,120,136],"information":[40,95],"plays":[41],"pivotal":[43],"role":[44],"not":[45,64],"only":[46],"during":[47,52,103,111],"network":[48,102,160],"training":[49],"but":[50,105],"also":[51],"testing.":[53,112],"However,":[54],"due":[55],"various":[57],"factors":[58],"real":[60],"environments,":[61],"sensors":[62],"do":[63],"always":[65],"possible":[66],"obtain":[68],"high-quality":[69],"signals.":[71],"this":[73,134],"paper,":[74],"we":[75],"propose":[76],"an":[77],"effective":[78],"two-stage":[79,187],"model":[83],"that":[84,205],"introduces":[85],"new":[87],"approach":[88],"feature":[91],"embedding,":[92],"where":[93],"is":[96,109,151,172,192],"optimize":[99],"the":[100,115,127,130,146,156,195,206],"training,":[104],"no":[106],"input":[108,128],"required":[110],"Different":[113],"from":[114],"methods":[117],"which":[118,150],"fuse":[119],"features":[121,124,137],"audio":[123],"together":[125],"network,":[132],"model,":[135],"are":[138,183],"embedded":[139],"into":[140],"matching":[142],"block":[143],"calculate":[145],"cross-modal":[147],"consistency":[148],"loss,":[149],"part":[154],"loss":[157,165],"function":[158,166],"for":[159,174],"optimization.":[161],"A":[162],"novel":[163],"tuples":[164],"with":[167],"learnable":[169],"dynamic":[170],"margin":[171,180],"proposed":[173,186],"better":[175],"matching,":[177],"two":[179],"change":[181],"strategies":[182],"given.":[184],"The":[185],"method":[191],"evaluated":[193],"on":[194],"widely":[196],"GRID":[198],"VoxCeleb2":[200],"datasets.":[201],"Experimental":[202],"results":[203],"show":[204],"performance":[207],"outperforms":[208],"methods.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}