{"id":"https://openalex.org/W3216920799","doi":"https://doi.org/10.1109/taslp.2021.3129335","title":"Multi-Channel Multi-Frame ADL-MVDR for Target Speech Separation","display_name":"Multi-Channel Multi-Frame ADL-MVDR for Target Speech Separation","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3216920799","doi":"https://doi.org/10.1109/taslp.2021.3129335","mag":"3216920799"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3129335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3129335","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language 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/A5078783442","display_name":"Zhuohuang Zhang","orcid":"https://orcid.org/0000-0003-3342-323X"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhuohuang Zhang","raw_affiliation_strings":["Computer Science, Indiana University Bloomington, 1771 Bloomington, Indiana, United States, 47405-7000 (e-mail: zhuozhan@iu.edu)","[Computer Science, Indiana University Bloomington, 1771 Bloomington, Indiana, United States, 47405-7000 (e-mail: zhuozhan@iu.edu)]"],"affiliations":[{"raw_affiliation_string":"Computer Science, Indiana University Bloomington, 1771 Bloomington, Indiana, United States, 47405-7000 (e-mail: zhuozhan@iu.edu)","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"[Computer Science, Indiana University Bloomington, 1771 Bloomington, Indiana, United States, 47405-7000 (e-mail: zhuozhan@iu.edu)]","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101467338","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0003-4944-6890"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":["Tencent, 508929 Bellevue, Washington, United States, 98004 (e-mail: lucayongxu@tencent.com)","[Tencent, 508929 Bellevue, Washington, United States, 98004 (e-mail: lucayongxu@tencent.com)]"],"affiliations":[{"raw_affiliation_string":"Tencent, 508929 Bellevue, Washington, United States, 98004 (e-mail: lucayongxu@tencent.com)","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"[Tencent, 508929 Bellevue, Washington, United States, 98004 (e-mail: lucayongxu@tencent.com)]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407019","display_name":"Meng Yu","orcid":"https://orcid.org/0000-0002-0031-9156"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, Washington, United States, (e-mail: raymondmyu@tencent.com)","[Tencent AI Lab, Bellevue, Washington, United States, (e-mail: raymondmyu@tencent.com)]"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, Washington, United States, (e-mail: raymondmyu@tencent.com)","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"[Tencent AI Lab, Bellevue, Washington, United States, (e-mail: raymondmyu@tencent.com)]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056567731","display_name":"Shixiong Zhang","orcid":"https://orcid.org/0000-0002-0314-9199"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi-Xiong Zhang","raw_affiliation_strings":["Tencent AI Lab, Bellevue, Washington, United States, 98004 (e-mail: auszhang@tencent.com)","[Tencent AI Lab, Bellevue, Washington, United States, 98004 (e-mail: auszhang@tencent.com)]"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, Washington, United States, 98004 (e-mail: auszhang@tencent.com)","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"[Tencent AI Lab, Bellevue, Washington, United States, 98004 (e-mail: auszhang@tencent.com)]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072495935","display_name":"Lianwu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianwu Chen","raw_affiliation_strings":["Tencent AI Lab, 546374 Shenzhen, Guangdong, China, (e-mail: lianwuchen@tencent.com)","[Tencent AI Lab, 546374 Shenzhen, Guangdong, China, (e-mail: lianwuchen@tencent.com)]"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, 546374 Shenzhen, Guangdong, China, (e-mail: lianwuchen@tencent.com)","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"[Tencent AI Lab, 546374 Shenzhen, Guangdong, China, (e-mail: lianwuchen@tencent.com)]","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054209447","display_name":"Donald S. Williamson","orcid":"https://orcid.org/0000-0002-7997-5403"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donald S. Williamson","raw_affiliation_strings":["School of Informatics and Computing, Indiana University, Bloomington, Indiana, United States, 47405 (e-mail: williads@indiana.edu)","[School of Informatics and Computing, Indiana University, Bloomington, Indiana, United States, 47405 (e-mail: williads@indiana.edu)]"],"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing, Indiana University, Bloomington, Indiana, United States, 47405 (e-mail: williads@indiana.edu)","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"[School of Informatics and Computing, Indiana University, Bloomington, Indiana, United States, 47405 (e-mail: williads@indiana.edu)]","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I70745867","display_name":"KLA (United States)","ror":"https://ror.org/02rqhpa98","country_code":"US","type":"company","lineage":["https://openalex.org/I70745867"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, Washington, United States, (e-mail: dyu@tencent.com)","[Tencent AI Lab, Bellevue, Washington, United States, (e-mail: dyu@tencent.com)]"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, Washington, United States, (e-mail: dyu@tencent.com)","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"[Tencent AI Lab, Bellevue, Washington, United States, (e-mail: dyu@tencent.com)]","institution_ids":["https://openalex.org/I70745867"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5078783442"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":3.6933,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.941212,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"3526","last_page":"3540"},"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":0.9987999796867371,"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":0.9983999729156494,"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":0.7586454153060913},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6311632394790649},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5666687488555908},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5547288656234741},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5076714754104614},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4999277591705322},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4762996435165405},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.47313323616981506},{"id":"https://openalex.org/keywords/minimum-variance-unbiased-estimator","display_name":"Minimum-variance unbiased estimator","score":0.46955564618110657},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4675879180431366},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42541569471359253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3438687324523926},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24285843968391418},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19230741262435913},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.14914998412132263},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14693689346313477},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09940233826637268},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09246903657913208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7586454153060913},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6311632394790649},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5666687488555908},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5547288656234741},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5076714754104614},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4999277591705322},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4762996435165405},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.47313323616981506},{"id":"https://openalex.org/C165646398","wikidata":"https://www.wikidata.org/wiki/Q3755281","display_name":"Minimum-variance unbiased estimator","level":3,"score":0.46955564618110657},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4675879180431366},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42541569471359253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3438687324523926},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24285843968391418},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19230741262435913},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.14914998412132263},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14693689346313477},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09940233826637268},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09246903657913208},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3129335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3129335","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":90,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1509088290","https://openalex.org/W1552314771","https://openalex.org/W1574203583","https://openalex.org/W1677182931","https://openalex.org/W1897240248","https://openalex.org/W1997270899","https://openalex.org/W1999405021","https://openalex.org/W2021525189","https://openalex.org/W2037951967","https://openalex.org/W2058079016","https://openalex.org/W2058986241","https://openalex.org/W2060108923","https://openalex.org/W2061074721","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2094287371","https://openalex.org/W2101609516","https://openalex.org/W2112469598","https://openalex.org/W2113969889","https://openalex.org/W2117678320","https://openalex.org/W2120608389","https://openalex.org/W2127851351","https://openalex.org/W2129934596","https://openalex.org/W2130317597","https://openalex.org/W2130537519","https://openalex.org/W2141998673","https://openalex.org/W2147002892","https://openalex.org/W2147665979","https://openalex.org/W2149591378","https://openalex.org/W2158143227","https://openalex.org/W2289480995","https://openalex.org/W2294167355","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2402526332","https://openalex.org/W2406737436","https://openalex.org/W2408713104","https://openalex.org/W2432567885","https://openalex.org/W2506203739","https://openalex.org/W2517616541","https://openalex.org/W2531409750","https://openalex.org/W2586584460","https://openalex.org/W2622589392","https://openalex.org/W2640112133","https://openalex.org/W2714487941","https://openalex.org/W2718052359","https://openalex.org/W2752530932","https://openalex.org/W2763687632","https://openalex.org/W2766876424","https://openalex.org/W2767071179","https://openalex.org/W2793459270","https://openalex.org/W2808920027","https://openalex.org/W2889411318","https://openalex.org/W2890489755","https://openalex.org/W2890553422","https://openalex.org/W2891378882","https://openalex.org/W2891984996","https://openalex.org/W2899963229","https://openalex.org/W2909607850","https://openalex.org/W2921824436","https://openalex.org/W2939497224","https://openalex.org/W2945191446","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2962905190","https://openalex.org/W2962935966","https://openalex.org/W2963045393","https://openalex.org/W2963308316","https://openalex.org/W2963341071","https://openalex.org/W2963452667","https://openalex.org/W2972693890","https://openalex.org/W2973231102","https://openalex.org/W2974407961","https://openalex.org/W3011424113","https://openalex.org/W3032514799","https://openalex.org/W3096008106","https://openalex.org/W3097173744","https://openalex.org/W3097213357","https://openalex.org/W3097966334","https://openalex.org/W3099330747","https://openalex.org/W3101330598","https://openalex.org/W3109458322","https://openalex.org/W3162315798","https://openalex.org/W3162341667","https://openalex.org/W4288366110","https://openalex.org/W6630309668","https://openalex.org/W6696933143","https://openalex.org/W6751512325","https://openalex.org/W6761806390"],"related_works":["https://openalex.org/W2560215812","https://openalex.org/W2071676784","https://openalex.org/W2949601986","https://openalex.org/W2788972299","https://openalex.org/W2463762105","https://openalex.org/W2166923183","https://openalex.org/W1572562701","https://openalex.org/W2005426889","https://openalex.org/W2380964641","https://openalex.org/W2394058734"],"abstract_inverted_index":{"Many":[0],"purely":[1],"neural":[2,47,77],"network":[3],"based":[4],"speech":[5,28,95],"separation":[6],"approaches":[7],"have":[8],"been":[9],"proposed":[10,105,123,126,149],"to":[11,25,41],"improve":[12],"objective":[13,157],"assessment":[14],"scores,":[15],"but":[16],"they":[17],"often":[18,39],"introduce":[19],"nonlinear":[20,43,112],"distortions":[21],"that":[22],"are":[23,38,117,128,136],"harmful":[24],"modern":[26],"automatic":[27],"recognition":[29],"(ASR)":[30],"systems.":[31],"Minimum":[32],"variance":[33],"distortionless":[34],"response":[35],"(MVDR)":[36],"filters":[37],"adopted":[40],"remove":[42],"distortions,":[44],"however,":[45],"conventional":[46],"mask-based":[48],"MVDR":[49,67],"systems":[50,127,150],"still":[51],"result":[52],"in":[53,65,121],"relatively":[54],"high":[55],"levels":[56],"of":[57,147],"residual":[58],"noise.":[59],"Moreover,":[60],"the":[61,66,122,145],"matrix":[62],"inverse":[63],"involved":[64],"solution":[68],"is":[69],"sometimes":[70],"numerically":[71],"unstable":[72],"during":[73],"joint":[74],"training":[75],"with":[76,138],"networks.":[78],"In":[79],"this":[80],"study,":[81],"we":[82],"propose":[83],"a":[84,131],"multi-channel":[85,101],"multi-frame":[86],"(MCMF)":[87],"all":[88],"deep":[89],"learning":[90],"(ADL)-MVDR":[91],"approach":[92],"for":[93],"target":[94],"separation,":[96],"which":[97],"extends":[98],"our":[99,148],"preliminary":[100],"ADL-MVDR":[102,107],"approach.":[103,124],"The":[104,125],"MCMF":[106],"system":[108],"addresses":[109],"linear":[110],"and":[111,135,154],"distortions.":[113],"Spatio-temporal":[114],"cross":[115],"correlations":[116],"also":[118],"fully":[119],"utilized":[120],"evaluated":[129],"using":[130],"Mandarin":[132],"audio-visual":[133],"corpus":[134],"compared":[137],"several":[139,156],"state-of-the-art":[140],"approaches.":[141],"Experimental":[142],"results":[143],"demonstrate":[144],"superiority":[146],"under":[151],"different":[152],"scenarios":[153],"across":[155],"evaluation":[158],"metrics,":[159],"including":[160],"ASR":[161],"performance.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}