{"id":"https://openalex.org/W4372263384","doi":"https://doi.org/10.1109/icassp49357.2023.10096255","title":"Investigating Content-Aware Neural Text-to-Speech MOS Prediction Using Prosodic and Linguistic Features","display_name":"Investigating Content-Aware Neural Text-to-Speech MOS Prediction Using Prosodic and Linguistic Features","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372263384","doi":"https://doi.org/10.1109/icassp49357.2023.10096255"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5015840293","display_name":"Alexandra Vioni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandra Vioni","raw_affiliation_strings":["Samsung Electronics,Innoetics,Greece","Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Innoetics,Greece","institution_ids":[]},{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037667852","display_name":"Georgia Maniati","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georgia Maniati","raw_affiliation_strings":["Samsung Electronics,Innoetics,Greece","Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Innoetics,Greece","institution_ids":[]},{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052196585","display_name":"Nikolaos Ellinas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolaos Ellinas","raw_affiliation_strings":["Samsung Electronics,Innoetics,Greece","Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Innoetics,Greece","institution_ids":[]},{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110947099","display_name":"June Sig Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"June Sig Sung","raw_affiliation_strings":["Samsung Electronics,Mobile eXperience Business,Republic of Korea","Mobile eXperience Business, Samsung Electronics, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Mobile eXperience Business,Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Mobile eXperience Business, Samsung Electronics, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101882326","display_name":"In-Chul Hwang","orcid":"https://orcid.org/0000-0002-0045-9984"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Inchul Hwang","raw_affiliation_strings":["Samsung Electronics,Mobile eXperience Business,Republic of Korea","Mobile eXperience Business, Samsung Electronics, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Mobile eXperience Business,Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Mobile eXperience Business, Samsung Electronics, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091595884","display_name":"Aimilios Chalamandaris","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aimilios Chalamandaris","raw_affiliation_strings":["Samsung Electronics,Innoetics,Greece","Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Innoetics,Greece","institution_ids":[]},{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027494724","display_name":"Pirros Tsiakoulis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pirros Tsiakoulis","raw_affiliation_strings":["Samsung Electronics,Innoetics,Greece","Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Innoetics,Greece","institution_ids":[]},{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1421,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82027533,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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":0.9970999956130981,"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/naturalness","display_name":"Naturalness","score":0.8498839735984802},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7262174487113953},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6180384159088135},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.533238410949707},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5305704474449158},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4927404224872589},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4808664917945862},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.44871100783348083},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3655305504798889}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8498839735984802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7262174487113953},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6180384159088135},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.533238410949707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5305704474449158},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4927404224872589},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4808664917945862},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.44871100783348083},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3655305504798889},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.550000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W70888257","https://openalex.org/W2105854852","https://openalex.org/W2107831318","https://openalex.org/W2511311723","https://openalex.org/W2557915412","https://openalex.org/W2895146711","https://openalex.org/W2896457183","https://openalex.org/W2963035245","https://openalex.org/W2963403924","https://openalex.org/W2963521945","https://openalex.org/W2970641574","https://openalex.org/W2972394484","https://openalex.org/W3016473712","https://openalex.org/W3091928890","https://openalex.org/W3095389792","https://openalex.org/W3097206152","https://openalex.org/W3161558238","https://openalex.org/W3163003432","https://openalex.org/W3196225973","https://openalex.org/W3198270377","https://openalex.org/W3202278141","https://openalex.org/W3207932315","https://openalex.org/W4223503417","https://openalex.org/W4225956675","https://openalex.org/W4296068832","https://openalex.org/W4296068974","https://openalex.org/W4297570641","https://openalex.org/W4395681663","https://openalex.org/W6676245417","https://openalex.org/W6729924827","https://openalex.org/W6755207826","https://openalex.org/W6776148200","https://openalex.org/W6784545093","https://openalex.org/W6865327743","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W169399214","https://openalex.org/W4214652783","https://openalex.org/W3100825170","https://openalex.org/W258725851","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W2108985546","https://openalex.org/W2433276473"],"abstract_inverted_index":{"Current":[0],"state-of-the-art":[1],"methods":[2],"for":[3,65],"automatic":[4],"synthetic":[5],"speech":[6,43,66],"evaluation":[7],"are":[8,123,143],"based":[9],"on":[10,33,90,125],"MOS":[11,16,83,120,134,147,154],"prediction":[12,17,84,92,121,148],"neural":[13,50,128],"models.":[14],"Such":[15],"models":[18],"include":[19,74],"MOSNet":[20],"and":[21,29,76,86,98,112,164],"LDNet":[22],"that":[23,31,39,138],"use":[24],"spectral":[25],"features":[26,78,100,142],"as":[27,45,79,101,104,106,115],"input,":[28],"SSL-MOS":[30],"relies":[32],"a":[34,62,127],"pretrained":[35],"selfsupervised":[36],"learning":[37],"model":[38],"directly":[40],"uses":[41],"the":[42,58,91,139,146,152,158],"signal":[44],"input.":[46],"In":[47],"modern":[48],"high-quality":[49],"TTS":[51],"systems,":[52,85],"prosodic":[53,75,102],"appropriateness":[54],"with":[55,131,157],"regard":[56],"to":[57,73],"spoken":[59],"content":[60],"is":[61],"decisive":[63],"factor":[64],"naturalness.":[67],"For":[68],"this":[69],"reason,":[70],"we":[71],"propose":[72],"linguistic":[77,117],"additional":[80,141],"inputs":[81],"in":[82,145],"evaluate":[87],"their":[88],"impact":[89],"outcome.":[93],"We":[94],"consider":[95],"phoneme-level":[96],"F0":[97],"duration":[99],"inputs,":[103],"well":[105],"Tacotron":[107],"encoder":[108],"outputs,":[109],"POS":[110],"tags":[111],"BERT":[113],"embeddings":[114],"higher-level":[116],"inputs.":[118],"All":[119],"systems":[122],"trained":[124],"SOMOS,":[126],"TTS-only":[129],"dataset":[130],"crowdsourced":[132],"naturalness":[133],"evaluations.":[135],"Results":[136],"show":[137],"proposed":[140],"beneficial":[144],"task,":[149],"by":[150],"improving":[151],"predicted":[153],"scores\u2019":[155],"correlation":[156],"ground":[159],"truths,":[160],"both":[161],"at":[162],"utterance-level":[163],"system-level":[165],"predictions.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2023-05-07T00:00:00"}
