{"id":"https://openalex.org/W4401611704","doi":"https://doi.org/10.1109/icasspw62465.2024.10627296","title":"Training Strategies for Modality Dropout Resilient Multi-Modal Target Speaker Extraction","display_name":"Training Strategies for Modality Dropout Resilient Multi-Modal Target Speaker Extraction","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401611704","doi":"https://doi.org/10.1109/icasspw62465.2024.10627296"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10627296","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10627296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5077147264","display_name":"Srikanth Korse","orcid":"https://orcid.org/0009-0008-7564-9628"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Srikanth Korse","raw_affiliation_strings":["International Audio Laboratories Erlangen,Erlangen,Germany,91058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080306514","display_name":"Mohamed Elminshawi","orcid":"https://orcid.org/0000-0003-2737-0602"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mohamed Elminshawi","raw_affiliation_strings":["International Audio Laboratories Erlangen,Erlangen,Germany,91058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031626756","display_name":"Emanu\u00ebl A. P. Habets","orcid":"https://orcid.org/0000-0002-2613-8046"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Emanu\u00ebl A. P. Habets","raw_affiliation_strings":["International Audio Laboratories Erlangen,Erlangen,Germany,91058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004929413","display_name":"Srikanth Raj Chetupalli","orcid":"https://orcid.org/0000-0002-2186-5420"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Srikanth Raj Chetupalli","raw_affiliation_strings":["International Audio Laboratories Erlangen,Erlangen,Germany,91058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210123192"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10498375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"595","last_page":"599"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9936000108718872,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9936000108718872,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9652000069618225,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.6922211647033691},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6851989030838013},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6392281651496887},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5738197565078735},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5138099789619446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4698193371295929},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4543151557445526},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35604357719421387},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19458577036857605},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.08113056421279907}],"concepts":[{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.6922211647033691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6851989030838013},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6392281651496887},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5738197565078735},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5138099789619446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4698193371295929},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4543151557445526},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35604357719421387},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19458577036857605},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.08113056421279907},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10627296","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10627296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2170864449","https://openalex.org/W2194775991","https://openalex.org/W2891205112","https://openalex.org/W2891833136","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2963192057","https://openalex.org/W2963528589","https://openalex.org/W2964058413","https://openalex.org/W2972513594","https://openalex.org/W2972568703","https://openalex.org/W3008400075","https://openalex.org/W3015199127","https://openalex.org/W3015636705","https://openalex.org/W3016361963","https://openalex.org/W3094612121","https://openalex.org/W3094806148","https://openalex.org/W3099330747","https://openalex.org/W3103434036","https://openalex.org/W3136499730","https://openalex.org/W3148386121","https://openalex.org/W3162534564","https://openalex.org/W3163287738","https://openalex.org/W3185109982","https://openalex.org/W4226115251","https://openalex.org/W4295308317","https://openalex.org/W4297841507","https://openalex.org/W4312852648","https://openalex.org/W6631190155","https://openalex.org/W6754420807","https://openalex.org/W6780226713","https://openalex.org/W6810827206"],"related_works":["https://openalex.org/W3082178636","https://openalex.org/W2782041652","https://openalex.org/W2612657834","https://openalex.org/W2392157706","https://openalex.org/W2599192953","https://openalex.org/W2952088488","https://openalex.org/W1521968289","https://openalex.org/W4225691210","https://openalex.org/W2481230473","https://openalex.org/W627697492"],"abstract_inverted_index":{"The":[0],"primary":[1],"goal":[2],"of":[3,45,61,78,103,136],"multi-modal":[4],"TSE":[5],"(MTSE)":[6],"is":[7,48,176,196],"to":[8,31,39,112,132,154,178],"extract":[9],"a":[10,14,87,109],"target":[11,33,194],"speaker":[12,195],"from":[13,20,56,124],"speech":[15,181],"mixture":[16],"using":[17,179],"complementary":[18],"information":[19],"different":[21],"modalities,":[22],"such":[23],"as":[24,108,182],"audio":[25],"enrolment":[26,184],"and":[27,75,94,114,149,157],"visual":[28],"feeds":[29],"corresponding":[30],"the":[32,46,52,62,65,76,82,101,125,129,137,143,147,162,170,183,193],"speaker.":[34],"MTSE":[35,89],"systems":[36,53],"are":[37,152],"expected":[38],"perform":[40],"well":[41],"even":[42],"when":[43],"one":[44,60],"modalities":[47,63],"unavailable.":[49],"In":[50,97,141],"practice,":[51],"often":[54],"suffer":[55],"modality":[57,104,155],"dominance,":[58,156],"where":[59,192],"outweighs":[64],"others,":[66],"thereby":[67],"limiting":[68],"robustness.":[69],"Our":[70],"study":[71],"investigates":[72],"training":[73,106,116],"strategies":[74,151],"effect":[77],"architectural":[79],"choices,":[80],"particularly":[81],"normalization":[83,139,164],"layers,":[84],"in":[85,91,190],"yielding":[86],"robust":[88,177],"system":[90,171],"both":[92],"non-causal":[93],"causal":[95],"configurations.":[96],"particular,":[98],"we":[99,167],"propose":[100],"use":[102],"dropout":[105],"(MDT)":[107],"superior":[110],"strategy":[111,131,175],"standard":[113,148],"multi-task":[115],"(MTT)":[117],"strategies.":[118],"Experiments":[119],"conducted":[120],"on":[121,161],"two-speaker":[122],"mixtures":[123],"LRS3":[126],"dataset":[127],"show":[128],"MDT":[130,174],"be":[133],"effective":[134],"irrespective":[135],"employed":[138],"layer.":[140,165],"contrast,":[142],"models":[144],"trained":[145,172],"with":[146,173],"MTT":[150],"susceptible":[153],"their":[158],"performance":[159],"depends":[160],"chosen":[163],"Additionally,":[166],"demonstrate":[168],"that":[169],"extracted":[180],"signal,":[185],"highlighting":[186],"its":[187],"potential":[188],"applicability":[189],"scenarios":[191],"not":[197],"enrolled.":[198]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}