{"id":"https://openalex.org/W4385822632","doi":"https://doi.org/10.21437/interspeech.2023-2078","title":"ASR and Emotional Speech: A Word-Level Investigation of the Mutual Impact of Speech and Emotion Recognition","display_name":"ASR and Emotional Speech: A Word-Level Investigation of the Mutual Impact of Speech and Emotion Recognition","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822632","doi":"https://doi.org/10.21437/interspeech.2023-2078"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2078","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/files/352261159/INTERSPEECH2023_ASR_emotion_.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077749078","display_name":"Yuanchao Li","orcid":"https://orcid.org/0000-0002-8005-947X"},"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"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yuanchao Li","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100775936","display_name":"Zeyu Zhao","orcid":"https://orcid.org/0009-0002-6612-9731"},"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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zeyu Zhao","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044666169","display_name":"Ond\u0159ej Klejch","orcid":"https://orcid.org/0000-0001-5495-967X"},"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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ond\u0159ej Klejch","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"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/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Catherine Lai","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5077749078"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":2.505,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.91370555,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1449","last_page":"1453"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8672000169754028,"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":0.8672000169754028,"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":0.801800012588501,"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/T12031","display_name":"Speech and dialogue systems","score":0.7267000079154968,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.690393328666687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6505724191665649},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6465035676956177},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5331335067749023},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4565446376800537},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2920805811882019}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.690393328666687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6505724191665649},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6465035676956177},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5331335067749023},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4565446376800537},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2920805811882019},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2023-2078","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/f3e454ed-232b-424b-8234-09c58e6d79a5","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/352261159/INTERSPEECH2023_ASR_emotion_.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Li, Y, Zhao, Z, Klejch, O, Bell, P & Lai, C 2023, ASR and Emotional Speech : A Word-Level Investigation of the Mutual Impact of Speech and Emotion Recognition. in Proc. INTERSPEECH 2023. Interspeech, International Speech Communication Association, pp. 1449-1453, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-2078","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/f3e454ed-232b-424b-8234-09c58e6d79a5","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f3e454ed-232b-424b-8234-09c58e6d79a5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Li, Y, Zhao, Z, Klejch, O, Bell, P & Lai, C 2023, ASR and Emotional Speech : A Word-Level Investigation of the Mutual Impact of Speech and Emotion Recognition. in Proc. INTERSPEECH 2023. Interspeech, International Speech Communication Association, pp. 1449-1453, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-2078","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/f3e454ed-232b-424b-8234-09c58e6d79a5","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/352261159/INTERSPEECH2023_ASR_emotion_.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Li, Y, Zhao, Z, Klejch, O, Bell, P & Lai, C 2023, ASR and Emotional Speech : A Word-Level Investigation of the Mutual Impact of Speech and Emotion Recognition. in Proc. INTERSPEECH 2023. Interspeech, International Speech Communication Association, pp. 1449-1453, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-2078","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4099999964237213,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1502400294","https://openalex.org/W1632114991","https://openalex.org/W2023736093","https://openalex.org/W2113258846","https://openalex.org/W2146334809","https://openalex.org/W2556418146","https://openalex.org/W2896457183","https://openalex.org/W2953320089","https://openalex.org/W2962770129","https://openalex.org/W2962780374","https://openalex.org/W2963686995","https://openalex.org/W2972602947","https://openalex.org/W2973034847","https://openalex.org/W2973110385","https://openalex.org/W3096757102","https://openalex.org/W3197947674","https://openalex.org/W4286890477","https://openalex.org/W4292529033","https://openalex.org/W4298071820","https://openalex.org/W4312237773","https://openalex.org/W4319862479"],"related_works":["https://openalex.org/W2360025963","https://openalex.org/W2360785147","https://openalex.org/W2789919619","https://openalex.org/W2293457016","https://openalex.org/W2353329674","https://openalex.org/W3169305685","https://openalex.org/W2351428524","https://openalex.org/W2368779261","https://openalex.org/W1551406738","https://openalex.org/W2610387714"],"abstract_inverted_index":{"In":[0],"Speech":[1,43],"Emotion":[2],"Recognition":[3,44],"(SER),":[4],"textual":[5],"data":[6],"is":[7,125],"often":[8],"used":[9],"alongside":[10],"audio":[11],"signals":[12],"to":[13,71,98,114,126,139,143],"address":[14],"their":[15],"inherent":[16],"variability.":[17],"However,":[18],"the":[19,29,52,60,128,147],"reliance":[20],"on":[21,47,55,106],"human":[22],"annotated":[23],"text":[24],"in":[25,68,137,151],"most":[26],"research":[27],"hinders":[28],"development":[30],"of":[31,62,122,133,149],"practical":[32],"SER":[33,105,150],"systems.":[34],"To":[35],"overcome":[36],"this":[37,123],"challenge,":[38],"we":[39,102],"investigate":[40,115],"how":[41,75,116],"Automatic":[42],"(ASR)":[45],"performs":[46],"emotional":[48,144],"speech":[49,145],"by":[50],"analyzing":[51],"ASR":[53,69,82,107,117,134,141],"performance":[54],"emotion":[56,76],"corpora":[57],"and":[58,65,89,91,96,130,135,146],"examining":[59],"distribution":[61],"word":[63,111],"errors":[64],"confidence":[66],"scores":[67],"transcripts":[70,108],"gain":[72],"insight":[73],"into":[74],"affects":[77,118],"ASR.":[78],"We":[79],"utilize":[80],"four":[81],"systems,":[83],"namely":[84],"Kaldi":[85],"ASR,":[86],"wav2vec,":[87],"Conformer,":[88],"Whisper,":[90],"three":[92],"corpora:":[93],"IEMOCAP,":[94],"MOSI,":[95],"MELD":[97],"ensure":[99],"generalizability.":[100],"Additionally,":[101],"conduct":[103],"text-based":[104],"with":[109],"increasing":[110],"error":[112],"rates":[113],"SER.":[119],"The":[120],"objective":[121],"study":[124],"uncover":[127],"relationship":[129],"mutual":[131],"impact":[132],"SER,":[136],"order":[138],"facilitate":[140],"adaptation":[142],"use":[148],"real":[152],"world.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}