{"id":"https://openalex.org/W7148490914","doi":"https://doi.org/10.1109/asru65441.2025.11434697","title":"ASR for Affective Speech: Investigating Impact of Emotion and Speech Generative Strategy","display_name":"ASR for Affective Speech: Investigating Impact of Emotion and Speech Generative Strategy","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148490914","doi":"https://doi.org/10.1109/asru65441.2025.11434697"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":null,"display_name":"Ya-Tse Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ya-Tse Wu","raw_affiliation_strings":["National Tsing Hua University,Department of Electrical Engineering,Hsinchu,Taiwan"],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Chi-Chun Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chi-Chun Lee","raw_affiliation_strings":["National Tsing Hua University,Hsinchu,Taiwan"],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81996977,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.8533999919891357,"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":0.8533999919891357,"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/T12684","display_name":"Stuttering Research and Treatment","score":0.019200000911951065,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical 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/T10403","display_name":"Phonetics and Phonology Research","score":0.015799999237060547,"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/affect","display_name":"Affect (linguistics)","score":0.30570000410079956},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3034999966621399},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.29840001463890076},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.28859999775886536}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5992000102996826},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4494999945163727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.33970001339912415},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3109000027179718},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2989000082015991},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2743000090122223}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.41652339696884155,"display_name":"Gender equality"}],"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/W1992475611","https://openalex.org/W2097888244","https://openalex.org/W2131055488","https://openalex.org/W2146334809","https://openalex.org/W2742542661","https://openalex.org/W2891138528","https://openalex.org/W2955663310","https://openalex.org/W3000558177","https://openalex.org/W3017022801","https://openalex.org/W3096147072","https://openalex.org/W3163573274","https://openalex.org/W3196475561","https://openalex.org/W4214913438","https://openalex.org/W4390874791","https://openalex.org/W4400615821","https://openalex.org/W4402111804","https://openalex.org/W4408355207","https://openalex.org/W4409361147","https://openalex.org/W4410766315","https://openalex.org/W4415540902"],"related_works":[],"abstract_inverted_index":{"This":[0],"work":[1],"investigates":[2],"how":[3],"emotional":[4,18,28,49,62],"speech":[5,14],"and":[6,21,46],"generative":[7,40],"strategies":[8],"affect":[9],"ASR":[10,93],"performance.":[11],"We":[12],"analyze":[13],"synthesized":[15],"from":[16],"three":[17],"TTS":[19],"models":[20],"find":[22],"that":[23],"substitution":[24],"errors":[25],"dominate,":[26],"with":[27],"expressiveness":[29],"varying":[30],"across":[31],"models.":[32],"Based":[33],"on":[34,60,67],"these":[35],"insights,":[36],"we":[37],"introduce":[38],"two":[39],"strategies:":[41],"one":[42],"using":[43,48],"transcription":[44],"correctness":[45],"another":[47],"salience,":[50],"to":[51],"construct":[52],"fine-tuning":[53],"subsets.":[54],"Results":[55],"show":[56],"consistent":[57],"WER":[58],"improvements":[59],"real":[61],"datasets":[63],"without":[64],"noticeable":[65],"degradation":[66],"clean":[68],"LibriSpeech":[69],"utterances.":[70],"The":[71],"combined":[72],"strategy":[73],"achieves":[74],"the":[75,85],"strongest":[76],"gains,":[77],"particularly":[78],"for":[79,90],"expressive":[80],"speech.":[81],"These":[82],"findings":[83],"highlight":[84],"importance":[86],"of":[87],"targeted":[88],"augmentation":[89],"building":[91],"emotion-aware":[92],"systems.":[94]},"counts_by_year":[],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2026-02-02T00:00:00"}