{"id":"https://openalex.org/W4416017960","doi":"https://doi.org/10.1145/3746252.3761206","title":"Hearing the Meaning, Not the Mess: Beyond Literal Transcription for Spoken Language","display_name":"Hearing the Meaning, Not the Mess: Beyond Literal Transcription for Spoken Language","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416017960","doi":"https://doi.org/10.1145/3746252.3761206"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761206","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","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/A5056914734","display_name":"Min Sun","orcid":"https://orcid.org/0009-0009-0071-5392"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Min Sun","raw_affiliation_strings":["China Mobile Information Technology Co., Ltd, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0009-0071-5392","affiliations":[{"raw_affiliation_string":"China Mobile Information Technology Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100305419","display_name":"Xu Ke","orcid":"https://orcid.org/0009-0000-6600-0554"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Xu","raw_affiliation_strings":["China Mobile Information Technology Co., Ltd, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0000-6600-0554","affiliations":[{"raw_affiliation_string":"China Mobile Information Technology Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024391533","display_name":"Jiarong Liu","orcid":"https://orcid.org/0009-0001-8963-5138"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiarong Liu","raw_affiliation_strings":["China Mobile Information Technology Co., Ltd, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0001-8963-5138","affiliations":[{"raw_affiliation_string":"China Mobile Information Technology Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014762616","display_name":"Jifan Yang","orcid":"https://orcid.org/0000-0003-1334-1827"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jifan Yang","raw_affiliation_strings":["China Mobile Information Technology Co., Ltd, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1334-1827","affiliations":[{"raw_affiliation_string":"China Mobile Information Technology Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109546253","display_name":"Yan Fang","orcid":"https://orcid.org/0009-0004-4434-4718"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Fang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-4434-4718","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042452580","display_name":"Weizheng Wang","orcid":"https://orcid.org/0000-0002-5879-585X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Weizheng Wang","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-5879-585X","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000977930","display_name":"Qipeng Xie","orcid":"https://orcid.org/0000-0002-5500-0249"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qipeng Xie","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5500-0249","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"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":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-1758-2870","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001188748","display_name":"Kaishun Wu","orcid":"https://orcid.org/0000-0003-2216-0737"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaishun Wu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2216-0737","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5056914734"],"corresponding_institution_ids":["https://openalex.org/I180662265"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16791723,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2811","last_page":"2820"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.17919999361038208,"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":0.17919999361038208,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.11150000244379044,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.0658000037074089,"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/transcription","display_name":"Transcription (linguistics)","score":0.7296000123023987},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5041999816894531},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.5020999908447266},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.47269999980926514},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.41609999537467957},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4092000126838684},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.39079999923706055},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.38580000400543213},{"id":"https://openalex.org/keywords/literal","display_name":"Literal (mathematical logic)","score":0.37380000948905945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7436000108718872},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7296000123023987},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5274999737739563},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5092999935150146},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5041999816894531},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.5020999908447266},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.47269999980926514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4496999979019165},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.41609999537467957},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.39079999923706055},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C2780882242","wikidata":"https://www.wikidata.org/wiki/Q14235582","display_name":"Literal (mathematical logic)","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C504583287","wikidata":"https://www.wikidata.org/wiki/Q1428637","display_name":"Spoken word","level":3,"score":0.36410000920295715},{"id":"https://openalex.org/C541956065","wikidata":"https://www.wikidata.org/wiki/Q2250680","display_name":"Speech error","level":3,"score":0.3407999873161316},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.29760000109672546},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C2987487971","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexical access","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C89267518","wikidata":"https://www.wikidata.org/wiki/Q179488","display_name":"Psycholinguistics","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.259799987077713},{"id":"https://openalex.org/C46182478","wikidata":"https://www.wikidata.org/wiki/Q7363315","display_name":"Literal and figurative language","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3761206","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2052666245","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2766219058","https://openalex.org/W3007227084","https://openalex.org/W3119308075","https://openalex.org/W3159481202","https://openalex.org/W3209984917","https://openalex.org/W4225297336","https://openalex.org/W4372270126","https://openalex.org/W4393161521","https://openalex.org/W4409348114","https://openalex.org/W4409363592"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,12,103,113,210,214,271],"rise":[2],"of":[3,16,105],"virtual":[4],"communication":[5],"and":[6,27,50,74,109,111,156,181,190,208,243],"smart":[7],"devices,":[8],"speech":[9,23],"has":[10],"become":[11],"most":[13],"natural":[14],"medium":[15],"interaction.":[17],"Yet":[18],"it":[19,160,198],"remains":[20],"intrinsically":[21],"difficult:":[22],"is":[24,265],"fleeting,":[25],"unstructured,":[26],"disfluent,":[28],"making":[29],"key":[30],"information":[31],"prone":[32],"to":[33,40,85,115,141,217],"loss.":[34],"Conventional":[35],"Speech-to-Text":[36],"(STT)":[37],"systems":[38],"attempt":[39],"acoustically":[41],"reconstruct":[42],"what":[43,66],"was":[44,67],"said.":[45],"However,":[46],"their":[47],"frame-level":[48],"alignment":[49],"rigid":[51],"token-by-token":[52],"decoding":[53],"break":[54],"down":[55],"under":[56,154,193],"noise,":[57],"interruptions,":[58],"or":[59],"fragmentation.":[60,157],"Humans,":[61],"in":[62,178,241,245,253,257,267],"contrast,":[63],"readily":[64],"grasp":[65],"meant":[68],"by":[69],"exploiting":[70],"syntax,":[71],"discourse,":[72],"pragmatics,":[73],"prosody.":[75],"We":[76],"argue":[77],"for":[78],"a":[79,125,134,162,200,238],"paradigm":[80],"shift":[81,98],"from":[82,91,94],"acoustic":[83],"reconstruction":[84],"semantic":[86,152,235],"transduction:":[87],"inferring":[88],"meaning":[89],"directly":[90],"speech,":[92],"abstracted":[93],"surface":[95],"distortions.":[96],"This":[97],"raises":[99],"two":[100],"challenges:":[101],"(C1)":[102],"lack":[104],"anchors":[106,169],"between":[107],"audio":[108],"meaning,":[110],"(C2)":[112],"need":[114],"maintain":[116],"compositional":[117,176],"semantics.":[118],"To":[119],"address":[120],"these,":[121],"we":[122],"introduce":[123],"CogTrans,":[124],"cognitively":[126],"inspired":[127],"speech-to-meaning":[128],"framework.":[129],"CogTrans":[130,187,232,264],"tackles":[131],"C1":[132],"through":[133],"Semantic":[135],"Anchor":[136],"Explorer,":[137],"built":[138],"on":[139,209],"I-JEPA":[140],"capture":[142],"higher-order":[143],"regularities,":[144],"prosodic":[145],"rhythms,":[146],"cross-frequency":[147],"coarticulation,":[148],"discourse":[149],"continuity-providing":[150],"resilient":[151],"scaffolds":[153],"noise":[155],"For":[158],"C2,":[159],"designs":[161],"Lexical-Semantic":[163],"Harmonizer":[164],"that":[165,186,263],"dynamically":[166],"integrates":[167],"these":[168,260],"with":[170,237],"lexical":[171],"embeddings;":[172],"thereby":[173],"preserving":[174],"fine-grained":[175],"fidelity":[177],"roles,":[179],"order,":[180],"entities.":[182],"Extensive":[183],"experiments":[184],"show":[185],"delivers":[188],"consistent":[189],"substantial":[191],"gains":[192],"challenging":[194],"conditions.":[195],"On":[196],"GigaSpeech,":[197],"achieves":[199],"6.58%":[201],"relative":[202],"Word":[203],"Error":[204],"Rate":[205],"(WER)":[206],"reduction,":[207],"multilingual":[211],"VoxPopuli":[212],"benchmark,":[213],"gain":[215],"climbs":[216],"12.97%":[218],"at":[219],"10":[220],"dB":[221],"noise-a":[222],"regime":[223],"where":[224,273],"conventional":[225],"models":[226],"typically":[227],"collapse.":[228],"Beyond":[229],"literal":[230],"accuracy,":[231],"also":[233,256],"boosts":[234],"fidelity,":[236],"3.40%":[239],"increase":[240],"ROUGE-L":[242],"3.45%":[244],"USE-Sim,":[246],"ensuring":[247],"transcripts":[248],"remain":[249],"faithful":[250],"not":[251],"only":[252],"words":[254],"but":[255],"meaning.":[258],"Together,":[259],"results":[261],"underscore":[262],"robust":[266],"noisy,":[268],"unconstrained":[269],"environments-precisely":[270],"conditions":[272],"reliability":[274],"matters":[275],"most.":[276]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-08T00:00:00"}