{"id":"https://openalex.org/W7225419976","doi":"https://doi.org/10.33774/coe-2026-jfxtt","title":"Beyond Transcription: Adaptation, Prosody and Vocal Expression in Speech AI","display_name":"Beyond Transcription: Adaptation, Prosody and Vocal Expression in Speech AI","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225419976","doi":"https://doi.org/10.33774/coe-2026-jfxtt"},"language":"en","primary_location":{"id":"doi:10.33774/coe-2026-jfxtt","doi":"https://doi.org/10.33774/coe-2026-jfxtt","is_oa":true,"landing_page_url":"https://doi.org/10.33774/coe-2026-jfxtt","pdf_url":"https://www.cambridge.org/engage/api-gateway/coe/assets/orp/resource/item/6aed608e9aeed8c6764393a4/original/beyond-transcription-adaptation-prosody-and-vocal-expression-in-speech-ai.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.cambridge.org/engage/api-gateway/coe/assets/orp/resource/item/6aed608e9aeed8c6764393a4/original/beyond-transcription-adaptation-prosody-and-vocal-expression-in-speech-ai.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027004405","display_name":"Nathan Roll","orcid":"https://orcid.org/0000-0003-2943-5684","observed_orcids":["https://orcid.org/0000-0003-2943-5684"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan Roll","raw_affiliation_strings":["Oruk","Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oruk","institution_ids":[]},{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068567791","display_name":"Calbert Graham","orcid":"https://orcid.org/0000-0002-9788-6295","observed_orcids":["https://orcid.org/0000-0002-9788-6295"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Calbert Graham","raw_affiliation_strings":["University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9794999957084656,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9794999957084656,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.017500000074505806,"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":0.0007999999797903001,"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/speech-emotion-recognition","display_name":"speech emotion recognition","score":0.9259999990463257},{"id":"https://openalex.org/keywords/emotion-labels","display_name":"emotion labels","score":0.3109999895095825},{"id":"https://openalex.org/keywords/crema-d","display_name":"CREMA-D","score":0.6959999799728394},{"id":"https://openalex.org/keywords/internal-representations","display_name":"internal representations","score":0.3490000069141388},{"id":"https://openalex.org/keywords/audio-editing","display_name":"audio editing","score":0.4090000092983246},{"id":"https://openalex.org/keywords/wavlm","display_name":"WavLM","score":0.8029999732971191},{"id":"https://openalex.org/keywords/prosody","display_name":"prosody","score":0.7609999775886536},{"id":"https://openalex.org/keywords/vocal-expression","display_name":"vocal expression","score":0.8759999871253967},{"id":"https://openalex.org/keywords/speech-adaptation","display_name":"speech adaptation","score":0.3720000088214874},{"id":"https://openalex.org/keywords/model-interpretability","display_name":"model interpretability","score":0.5}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7594000101089478},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6320000290870667},{"id":"https://openalex.org/C2781115785","wikidata":"https://www.wikidata.org/wiki/Q502261","display_name":"Silence","level":2,"score":0.6243000030517578},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5134999752044678},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5131999850273132},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5033000111579895},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.48240000009536743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47859999537467957},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3400999903678894},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.33309999108314514},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C2780378701","wikidata":"https://www.wikidata.org/wiki/Q7451195","display_name":"Sentence processing","level":3,"score":0.30300000309944153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2892000079154968},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26019999384880066},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.33774/coe-2026-jfxtt","doi":"https://doi.org/10.33774/coe-2026-jfxtt","is_oa":true,"landing_page_url":"https://doi.org/10.33774/coe-2026-jfxtt","pdf_url":"https://www.cambridge.org/engage/api-gateway/coe/assets/orp/resource/item/6aed608e9aeed8c6764393a4/original/beyond-transcription-adaptation-prosody-and-vocal-expression-in-speech-ai.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.33774/coe-2026-jfxtt","doi":"https://doi.org/10.33774/coe-2026-jfxtt","is_oa":true,"landing_page_url":"https://doi.org/10.33774/coe-2026-jfxtt","pdf_url":"https://www.cambridge.org/engage/api-gateway/coe/assets/orp/resource/item/6aed608e9aeed8c6764393a4/original/beyond-transcription-adaptation-prosody-and-vocal-expression-in-speech-ai.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225419976.pdf","grobid_xml":"https://content.openalex.org/works/W7225419976.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W3159900299","https://openalex.org/W3209984917"],"related_works":["https://openalex.org/W7045540007","https://openalex.org/W2150653833","https://openalex.org/W7222998415","https://openalex.org/W2972971501","https://openalex.org/W7204865072","https://openalex.org/W3097567450","https://openalex.org/W7096685101","https://openalex.org/W7067428631","https://openalex.org/W7215070229","https://openalex.org/W2972306978"],"abstract_inverted_index":{"Speech-emotion":[0],"models":[1],"assign":[2],"familiar":[3],"labels":[4,10,46],"such":[5],"as":[6],"\u201chappy\u201d,":[7,49],"but":[8],"those":[9,188],"need":[11],"not":[12],"correspond":[13],"to":[14,83,100],"the":[15,34,72,77,101,113,124,169],"distinctions":[16],"listeners":[17],"or":[18],"speakers":[19],"intend.":[20],"We":[21],"examine":[22],"what":[23],"drives":[24],"these":[25,157],"assignments":[26],"using":[27,134],"546":[28,119],"CREMA-D":[29,136,212],"recordings:":[30],"91":[31,53,59],"actors":[32],"producing":[33],"same":[35,125],"sentence":[36],"in":[37,89,147,153],"six":[38],"acted":[39,143,196],"emotional":[40],"deliveries.":[41],"Fourier,":[42],"Oruk\u2019s":[43],"speech-emotion":[44,184],"model,":[45],"247":[47],"recordings":[48,55,70],"including":[50],"74":[51],"of":[52,58,110,118],"acted-happy":[54],"and":[56,163,180,186,198,211],"71":[57],"acted-neutral":[60],"recordings.":[61],"Removing":[62],"one":[63],"internal":[64,161],"direction":[65],"estimated":[66],"from":[67,81],"other":[68],"actors\u2019":[69],"reduces":[71],"mean":[73],"happy":[74],"score":[75],"on":[76,95],"originally":[78],"tagged":[79],"clips":[80],"0.660":[82],"0.315;":[84],"64":[85],"random":[86],"edits":[87,166],"matched":[88],"size":[90],"leave":[91],"it":[92],"at":[93],"0.649":[94],"average.":[96],"A":[97,130],"simple":[98],"change":[99],"input":[102],"produces":[103],"a":[104,172],"comparable":[105],"effect:":[106],"adding":[107,123],"0.5":[108],"seconds":[109],"silence":[111,126],"before":[112,182],"unchanged":[114],"speech":[115],"alters":[116,128],"161":[117],"happy-tag":[120],"decisions,":[121],"whereas":[122],"afterwards":[127],"32.":[129],"separate":[131],"WavLM":[132],"analysis":[133],"different":[135],"takes":[137],"finds":[138],"that":[139],"representation":[140],"trajectories":[141],"distinguish":[142],"deliveries":[144],"most":[145],"strongly":[146],"early":[148],"layers,":[149],"with":[150,190],"separation":[151],"decreasing":[152],"later":[154],"layers.":[155],"Together,":[156],"results":[158],"show":[159],"how":[160],"interventions":[162],"controlled":[164],"audio":[165],"can":[167],"reveal":[168],"cues":[170],"underlying":[171],"model\u2019s":[173],"categories.":[174],"They":[175],"motivate":[176],"checking":[177],"padding,":[178],"amplitude":[179],"segmentation":[181],"interpreting":[183],"outputs,":[185],"comparing":[187],"outputs":[189],"listener":[191],"judgements.":[192],"The":[193],"findings":[194],"concern":[195],"portrayals":[197],"model":[199],"labels,":[200],"rather":[201],"than":[202],"speakers\u2019":[203],"felt":[204],"emotions;":[205],"overlap":[206],"between":[207],"Fourier\u2019s":[208],"training":[209],"data":[210],"cannot":[213],"be":[214],"excluded.":[215]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-07T00:00:00"}