{"id":"https://openalex.org/W7202200071","doi":"https://doi.org/10.18653/2026.emnlp-main.1857","title":"Beyond Naturalness: Probing Automated TTS Evaluators on Linguistically Grounded Dimensions","display_name":"Beyond Naturalness: Probing Automated TTS Evaluators on Linguistically Grounded Dimensions","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7202200071","doi":"https://doi.org/10.18653/2026.emnlp-main.1857"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.1857","doi":"https://doi.org/10.18653/2026.emnlp-main.1857","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1857","pdf_url":"https://aclanthology.org/2026.emnlp-main.1857.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-main.1857.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092998385","display_name":"Oluwanifemi Bamgbose","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oluwanifemi Bamgbose","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112737571","display_name":"Jash Shah","orcid":"https://orcid.org/0009-0000-6427-587X","observed_orcids":["https://orcid.org/0009-0000-6427-587X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jash Shah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126245206","display_name":"Simon Rosen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon Rosen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064260763","display_name":"Lindsay D. Brin","orcid":"https://orcid.org/0000-0003-0605-0394","observed_orcids":["https://orcid.org/0000-0003-0605-0394"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lindsay Devon Brin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146515294","display_name":"Hoang H Nguyen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoang H Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012392072","display_name":"Anke K\u00f6lzer","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anke Koelzer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146510590","display_name":"Rachel Hansen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rachel Hansen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119958354","display_name":"Tara Bogavelli","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tara Bogavelli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5122983652","display_name":"Fanny Riols","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanny Riols","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.51646225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"42215","last_page":"42243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.9984999895095825,"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":0.00039999998989515007,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0003000000142492354,"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/text-to-speech-evaluation","display_name":"text-to-speech evaluation","score":0.9710000157356262},{"id":"https://openalex.org/keywords/automated-assessment","display_name":"automated assessment","score":0.527999997138977},{"id":"https://openalex.org/keywords/naturalness","display_name":"naturalness","score":0.8619999885559082},{"id":"https://openalex.org/keywords/large-audio-language-models","display_name":"large audio language models","score":0.9340000152587891},{"id":"https://openalex.org/keywords/speech-errors","display_name":"speech errors","score":0.5529999732971191},{"id":"https://openalex.org/keywords/prosody","display_name":"prosody","score":0.8899999856948853},{"id":"https://openalex.org/keywords/paralanguage","display_name":"paralinguistic features","score":0.9079999923706055}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6710000038146973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6521000266075134},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6136000156402588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5317999720573425},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5218999981880188},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4993000030517578},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4936999976634979},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.45820000767707825},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38929998874664307},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2784000039100647},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.26840001344680786},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.2606000006198883},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.25679999589920044}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.1857","doi":"https://doi.org/10.18653/2026.emnlp-main.1857","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1857","pdf_url":"https://aclanthology.org/2026.emnlp-main.1857.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.09930","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.09930","pdf_url":"https://arxiv.org/pdf/2608.09930","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.09930","doi":"https://doi.org/10.48550/arxiv.2608.09930","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.09930","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.emnlp-main.1857","doi":"https://doi.org/10.18653/2026.emnlp-main.1857","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1857","pdf_url":"https://aclanthology.org/2026.emnlp-main.1857.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7202200071.pdf","grobid_xml":"https://content.openalex.org/works/W7202200071.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W3152626170","https://openalex.org/W3174758275","https://openalex.org/W4407310319","https://openalex.org/W4416189904","https://openalex.org/W4417538286","https://openalex.org/W7114773363","https://openalex.org/W7166803493"],"related_works":["https://openalex.org/W7125578198","https://openalex.org/W2051333662","https://openalex.org/W4386790405","https://openalex.org/W4416608681","https://openalex.org/W7104020312","https://openalex.org/W4417094178","https://openalex.org/W7166806503","https://openalex.org/W7221075149","https://openalex.org/W4414683987","https://openalex.org/W7015246337"],"abstract_inverted_index":{"Automated":[0],"Text-to-Speech":[1],"(TTS)":[2],"evaluation":[3,132],"methods":[4],"(Mean":[5],"Opinion":[6],"Score":[7],"(MOS)":[8],"predictors":[9,77,85],"and":[10,53,78,96,110,131,141],"Audio":[11],"Large":[12],"Language":[13],"Model":[14],"(Audio-LLM)":[15],"judges)":[16],"are":[17,86,134],"expected":[18],"to":[19,56,89,137],"reflect":[20],"human":[21],"perception,":[22],"yet":[23],"it":[24,55],"is":[25],"unclear":[26],"how":[27],"well":[28],"they":[29],"capture":[30],"the":[31,58,94],"distinct":[32,50],"aspects":[33],"of":[34,122],"speech":[35,126],"that":[36,83,106],"listeners":[37],"actually":[38],"perceive.We":[39],"deconstruct":[40],"\"naturalness\"":[41],"into":[42],"a":[43,120],"linguistically":[44,123],"grounded":[45],"annotation":[46,129],"schema":[47],"spanning":[48],"10":[49],"perceptual":[51],"dimensions,":[52],"use":[54],"construct":[57],"first":[59],"dimensionlevel":[60],"meta-evaluation":[61],"benchmark":[62],"for":[63],"TTS,":[64],"comprising":[65],"860":[66],"utterances":[67],"annotated":[68],"by":[69],"trained":[70],"linguist":[71],"raters.Results":[72],"from":[73],"benchmarking":[74],"four":[75,79],"MOS":[76,84],"Audio-LLM":[80,100],"judges":[81,101],"reveal":[82],"more":[87,139],"sensitive":[88],"acoustic":[90],"signal-level":[91],"properties":[92],"at":[93],"prosodic":[95],"paralinguistic":[97],"levels,":[98],"while":[99],"show":[102],"selective,":[103],"prompt-dependent":[104],"detection":[105],"favors":[107],"word-level":[108],"errors":[109],"does":[111],"not":[112],"generalize":[113],"across":[114],"all":[115],"dimensions.Neither":[116],"class":[117],"reliably":[118],"captures":[119],"breadth":[121],"structured,":[124],"human-perceptible":[125],"errors.Our":[127],"dataset,":[128],"schema,":[130],"code":[133],"publicly":[135],"released":[136],"support":[138],"targeted":[140],"interpretable":[142],"TTS":[143],"evaluation.":[144],"1":[145]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-08-12T00:00:00"}