{"id":"https://openalex.org/W4406461641","doi":"https://doi.org/10.1109/slt61566.2024.10832143","title":"Speech Emotion Recognition With ASR Transcripts: a Comprehensive Study on Word Error Rate and Fusion Techniques","display_name":"Speech Emotion Recognition With ASR Transcripts: a Comprehensive Study on Word Error Rate and Fusion Techniques","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461641","doi":"https://doi.org/10.1109/slt61566.2024.10832143"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5005643073","display_name":"Yuanchao Li","orcid":"https://orcid.org/0000-0003-4266-2005"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]},{"id":"https://openalex.org/I4210159188","display_name":"SpeechTech (Czechia)","ror":"https://ror.org/05fsqes40","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210159188"]}],"countries":["CZ","GB"],"is_corresponding":true,"raw_author_name":"Yuanchao Li","raw_affiliation_strings":["University of Edinburgh,Centre for Speech Technology Research"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Centre for Speech Technology Research","institution_ids":["https://openalex.org/I98677209","https://openalex.org/I4210159188"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[{"id":"https://openalex.org/I4210159188","display_name":"SpeechTech (Czechia)","ror":"https://ror.org/05fsqes40","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210159188"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["CZ","GB"],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["University of Edinburgh,Centre for Speech Technology Research"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Centre for Speech Technology Research","institution_ids":["https://openalex.org/I98677209","https://openalex.org/I4210159188"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058881584","display_name":"Catherine Lai","orcid":"https://orcid.org/0000-0003-2411-8954"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]},{"id":"https://openalex.org/I4210159188","display_name":"SpeechTech (Czechia)","ror":"https://ror.org/05fsqes40","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210159188"]}],"countries":["CZ","GB"],"is_corresponding":false,"raw_author_name":"Catherine Lai","raw_affiliation_strings":["University of Edinburgh,Centre for Speech Technology Research"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Centre for Speech Technology Research","institution_ids":["https://openalex.org/I98677209","https://openalex.org/I4210159188"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005643073"],"corresponding_institution_ids":["https://openalex.org/I4210159188","https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":5.3301,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.96214692,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"518","last_page":"525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9968000054359436,"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/T13289","display_name":"Infant Health and Development","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.8162928819656372},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7993930578231812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7322419881820679},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6381731033325195},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5877642631530762},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5057296752929688},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.49150145053863525},{"id":"https://openalex.org/keywords/error-analysis","display_name":"Error analysis","score":0.48341596126556396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44952359795570374},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.41829541325569153},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13547292351722717},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06622010469436646}],"concepts":[{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.8162928819656372},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7993930578231812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7322419881820679},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6381731033325195},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5877642631530762},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5057296752929688},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.49150145053863525},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.48341596126556396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44952359795570374},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.41829541325569153},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13547292351722717},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06622010469436646},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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":35,"referenced_works":["https://openalex.org/W2090987251","https://openalex.org/W2146334809","https://openalex.org/W2158061940","https://openalex.org/W2556418146","https://openalex.org/W2742542661","https://openalex.org/W2962770129","https://openalex.org/W2963091558","https://openalex.org/W2963686995","https://openalex.org/W2964010806","https://openalex.org/W2973034847","https://openalex.org/W2973110385","https://openalex.org/W2973518854","https://openalex.org/W3093051361","https://openalex.org/W3096723250","https://openalex.org/W3160222702","https://openalex.org/W3197236059","https://openalex.org/W3197947674","https://openalex.org/W3197977579","https://openalex.org/W3198528147","https://openalex.org/W3208480086","https://openalex.org/W4285107355","https://openalex.org/W4361994820","https://openalex.org/W4372266796","https://openalex.org/W4378464659","https://openalex.org/W4385822510","https://openalex.org/W4385822632","https://openalex.org/W4385823029","https://openalex.org/W4389520395","https://openalex.org/W4391057902","https://openalex.org/W4392903618","https://openalex.org/W4392904444","https://openalex.org/W4406461849","https://openalex.org/W6771467084","https://openalex.org/W6852678209","https://openalex.org/W7061706593"],"related_works":["https://openalex.org/W2099421762","https://openalex.org/W2530546662","https://openalex.org/W2967030268","https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W2152662039","https://openalex.org/W1529797273","https://openalex.org/W2137901323","https://openalex.org/W1596452184"],"abstract_inverted_index":{"Text":[0],"data":[1],"is":[2],"commonly":[3],"utilized":[4],"as":[5,49],"a":[6,35,93,110],"primary":[7],"input":[8],"to":[9,130],"enhance":[10],"Speech":[11,45],"Emotion":[12],"Recognition":[13,46],"(SER)":[14],"performance":[15,58],"and":[16,40,77,84,100,119,125],"reliability.":[17],"However,":[18],"the":[19,28,50,131],"reliance":[20],"on":[21,71],"human-transcribed":[22],"text":[23,51],"in":[24],"most":[25],"studies":[26],"impedes":[27],"development":[29],"of":[30],"practical":[31],"SER":[32,57,86,105,127,140],"systems,":[33],"creating":[34],"gap":[36],"between":[37],"in-lab":[38],"research":[39],"real-world":[41,146],"scenarios":[42],"where":[43],"Automatic":[44],"(ASR)":[47],"serves":[48],"source.":[52],"Hence,":[53],"this":[54],"study":[55],"benchmarks":[56],"using":[59],"ASR":[60,112,116,133,142],"transcripts":[61],"with":[62,87,141],"varying":[63],"Word":[64],"Error":[65],"Rates":[66],"(WERs)":[67],"from":[68],"eleven":[69],"models":[70],"three":[72],"well-known":[73],"corpora:":[74],"IEMOCAP,":[75],"CMU-MOSI,":[76],"MSP-Podcast.":[78],"Our":[79],"evaluation":[80],"includes":[81],"both":[82],"text-only":[83],"bimodal":[85],"six":[88],"fusion":[89],"techniques,":[90],"aiming":[91],"for":[92,145],"comprehensive":[94],"analysis":[95],"that":[96],"uncovers":[97],"novel":[98],"findings":[99,136],"challenges":[101],"faced":[102],"by":[103],"current":[104],"research.":[106],"Additionally,":[107],"we":[108],"propose":[109],"unified":[111],"error-robust":[113],"framework":[114],"integrating":[115],"error":[117],"correction":[118],"modality-gated":[120],"fusion,":[121],"achieving":[122],"lower":[123],"WER":[124],"higher":[126],"results":[128],"compared":[129],"best-performing":[132],"transcript.":[134],"These":[135],"provide":[137],"insights":[138],"into":[139],"assistance,":[143],"especially":[144],"applications.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}