{"id":"https://openalex.org/W4415709438","doi":"https://doi.org/10.1109/icme59968.2025.11210156","title":"Multi-modal Speech Transformer Decoders: When Do Multiple Modalities Improve Accuracy?","display_name":"Multi-modal Speech Transformer Decoders: When Do Multiple Modalities Improve Accuracy?","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709438","doi":"https://doi.org/10.1109/icme59968.2025.11210156"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5108942659","display_name":"Yiwen Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yiwen Guan","raw_affiliation_strings":["Worcester Polytechnic Institute"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085746637","display_name":"Viet Anh Trinh","orcid":"https://orcid.org/0000-0002-1660-6627"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viet Anh Trinh","raw_affiliation_strings":["Worcester Polytechnic Institute"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114369145","display_name":"Vivek Voleti","orcid":null},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivek Voleti","raw_affiliation_strings":["Worcester Polytechnic Institute"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027788582","display_name":"Jacob Whitehill","orcid":"https://orcid.org/0000-0002-5851-312X"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Whitehill","raw_affiliation_strings":["Worcester Polytechnic Institute"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute","institution_ids":["https://openalex.org/I107077323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108942659"],"corresponding_institution_ids":["https://openalex.org/I107077323"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42565475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9854999780654907,"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":0.9854999780654907,"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":0.008200000040233135,"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/T11448","display_name":"Face recognition and analysis","score":0.001500000013038516,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/modalities","display_name":"Modalities","score":0.8044000267982483},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.652400016784668},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6126999855041504},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.49059998989105225},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.45320001244544983},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3628999888896942}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.8044000267982483},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7269999980926514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7160999774932861},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.652400016784668},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6126999855041504},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.49059998989105225},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.45320001244544983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4212000072002411},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.29910001158714294},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.28360000252723694},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26179999113082886}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":21,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1861492603","https://openalex.org/W2890952074","https://openalex.org/W2972756321","https://openalex.org/W3081492798","https://openalex.org/W3162293946","https://openalex.org/W3196509775","https://openalex.org/W4223499953","https://openalex.org/W4297841641","https://openalex.org/W4319300051","https://openalex.org/W4321375307","https://openalex.org/W4372346152","https://openalex.org/W4380373744","https://openalex.org/W4386071467","https://openalex.org/W4392909068","https://openalex.org/W4392909790","https://openalex.org/W4402606299","https://openalex.org/W4402670135","https://openalex.org/W4402671247","https://openalex.org/W4404792841","https://openalex.org/W4408354236"],"related_works":[],"abstract_inverted_index":{"Decoder-only":[0],"discrete-token":[1],"language":[2],"models":[3],"have":[4],"recently":[5],"achieved":[6],"significant":[7],"success":[8],"in":[9,22,85],"automatic":[10],"speech":[11,38,87,97],"recognition.":[12],"However,":[13],"systematic":[14],"analyses":[15],"of":[16,34,65,77],"how":[17],"different":[18,112],"modalities":[19,36,54,118],"impact":[20],"performance":[21],"specific":[23],"scenarios":[24],"remain":[25],"limited.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30],"investigate":[31],"the":[32,59,63,72,75,132],"effects":[33],"multiple":[35],"on":[37,41,62,125],"recognition":[39,88,98],"accuracy":[40,57],"both":[42,126],"synthetic":[43,127],"and":[44,82,128],"real-world":[45,129],"datasets.":[46],"Our":[47],"experiments":[48],"suggest":[49],"that:":[50],"(1)":[51],"Integrating":[52],"more":[53],"can":[55],"increase":[56],"but":[58],"benefit":[60,76,102],"depends":[61],"amount":[64],"auditory":[66],"noise.":[67],"We":[68],"also":[69],"show":[70],"for":[71,96],"first":[73],"time":[74],"combining":[78],"audio,":[79],"image":[80],"context,":[81],"lip":[83,120],"information":[84,136],"one":[86],"model.":[89],"(2)":[90],"Images":[91],"as":[92,139],"a":[93,111,140],"supplementary":[94],"modality":[95],"provide":[99],"their":[100],"greatest":[101],"at":[103],"moderate":[104],"audio":[105],"noise":[106],"levels;":[107],"moreover,":[108],"they":[109],"exhibit":[110],"trend":[113],"compared":[114],"to":[115],"inherently":[116],"synchronized":[117],"like":[119],"movements.":[121],"(3)":[122],"Performance":[123],"improves":[124],"datasets":[130],"when":[131],"most":[133],"relevant":[134],"visual":[135],"is":[137],"filtered":[138],"preprocessing":[141],"step.":[142]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}