{"id":"https://openalex.org/W7166882825","doi":"https://doi.org/10.18653/v1/2026.acl-long.730","title":"Listening Like Humans: Semantics-Guided Noise-Robust Multimodal Speech Recognition","display_name":"Listening Like Humans: Semantics-Guided Noise-Robust Multimodal Speech Recognition","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166882825","doi":"https://doi.org/10.18653/v1/2026.acl-long.730"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.730","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.730","pdf_url":"https://aclanthology.org/2026.acl-long.730.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.730.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139761469","display_name":"Yan Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139831671","display_name":"Jun Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139744520","display_name":"Yian Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yian Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014020768","display_name":"Shuxin Zhong","orcid":"https://orcid.org/0009-0006-1758-2870"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuxin Zhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139798352","display_name":"Min Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139815353","display_name":"Kaishun Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaishun Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87110331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16079","last_page":"16093"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.41499999165534973,"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":0.41499999165534973,"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":0.2786000072956085,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.08250000327825546,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4659000039100647},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3089999854564667},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.2937999963760376},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2840999960899353},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2703000009059906}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6097000241279602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5231000185012817},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3433000147342682},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29840001463890076},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2937999963760376},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2745000123977661},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.730","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.730","pdf_url":"https://aclanthology.org/2026.acl-long.730.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.730","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.730","pdf_url":"https://aclanthology.org/2026.acl-long.730.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5483829975128174,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G2573870646","display_name":null,"funder_award_id":"2024GCZX003","funder_id":"https://openalex.org/F4320326279","funder_display_name":"Department of Education of Guangdong Province"},{"id":"https://openalex.org/G3965030583","display_name":null,"funder_award_id":"2023KCXTD042","funder_id":"https://openalex.org/F4320326279","funder_display_name":"Department of Education of Guangdong Province"},{"id":"https://openalex.org/G8000406786","display_name":null,"funder_award_id":"62472366","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8238644607","display_name":null,"funder_award_id":"2023B1212010007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8484321584","display_name":null,"funder_award_id":"ZDSYS20190902092853047","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8982764754","display_name":null,"funder_award_id":"D25008","funder_id":"https://openalex.org/F4320336698","funder_display_name":"Overseas Expertise Introduction Center for Discipline Innovation of Food Nutrition and Human Health (111 Center)"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326279","display_name":"Department of Education of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320336698","display_name":"Overseas Expertise Introduction Center for Discipline Innovation of Food Nutrition and Human Health (111 Center)","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166882825.pdf","grobid_xml":"https://content.openalex.org/works/W7166882825.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Severe":[0],"acoustic":[1,57,103],"degradation":[2],"is":[3],"often":[4],"caused":[5],"by":[6,28],"overlapping":[7],"noise,":[8,63],"disfluencies,":[9],"and":[10,21,64,85,116,149,161],"environmental":[11],"distortions.This":[12],"phenomenon":[13],"results":[14],"in":[15,142,158],"the":[16,22],"dissolution":[17],"of":[18,24,53],"linguistic":[19,54],"structures":[20],"generation":[23],"unreliable":[25],"ASR":[26,41,77],"outputs.Inspired":[27],"human":[29],"speech":[30,44],"comprehension,":[31],"we":[32,72],"propose":[33,73],"Speech-MLM,":[34,74],"a":[35,75,125],"novel":[36],"multimodal":[37,76],"framework":[38,78],"that":[39,79,97,108,121,135],"reframes":[40],"as":[42],"semantics-guided":[43],"reconstruction.This":[45],"perspective":[46],"introduces":[47],"three":[48],"core":[49],"challenges:":[50],"(C1)":[51],"collapse":[52],"structure":[55,100],"under":[56,62],"degradation,":[58],"(C2)":[59],"semantic":[60,110,127,159],"ambiguity":[61],"(C3)":[65],"misalignment":[66],"across":[67,112,163],"modalities.To":[68],"address":[69],"these":[70],"issues,":[71],"integrates":[80],"speech,":[81],"spectrogram-derived":[82],"visual":[83],"cues,":[84],"textual":[86,114],"variants":[87],"to":[88],"enhance":[89],"robustness.It":[90],"consists":[91],"of:":[92],"(i)":[93],"Cognitive":[94],"Structure":[95],"Extractor":[96],"recovers":[98],"prosodic":[99],"from":[101],"visualized":[102],"features,":[104],"(ii)":[105],"Semantic":[106],"Weaver":[107],"learns":[109],"equivalence":[111],"varied":[113],"forms,":[115],"(iii)":[117],"Retrieval-Guided":[118],"Fusion":[119],"Learner":[120],"unifies":[122],"modalities":[123],"within":[124],"shared":[126],"space.Experiments":[128],"on":[129],"multiple":[130],"real-world":[131],"noisy":[132],"datasets":[133],"demonstrate":[134],"Speech-MLM":[136],"achieves":[137],"an":[138],"average":[139],"38.85%":[140],"reduction":[141],"WER,":[143],"while":[144],"also":[145],"attaining":[146],"98.71%":[147],"BERTScore":[148],"96.7%":[150],"USE,":[151],"over":[152],"advanced":[153],"baselines,":[154],"demonstrating":[155],"substantial":[156],"gains":[157],"robustness":[160],"generalization":[162],"domains.":[164]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}