{"id":"https://openalex.org/W7148517151","doi":"https://doi.org/10.1109/asru65441.2025.11434769","title":"Layer-wise Analysis for Quality of Multilingual Synthesized Speech","display_name":"Layer-wise Analysis for Quality of Multilingual Synthesized Speech","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148517151","doi":"https://doi.org/10.1109/asru65441.2025.11434769"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434769","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":"https://openalex.org/A5082349516","display_name":"Erica Cooper","orcid":"https://orcid.org/0000-0002-2978-2793"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Erica Cooper","raw_affiliation_strings":["National Institute of Information and Communications Technology"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132826953","display_name":"Takuma Okamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuma Okamoto","raw_affiliation_strings":["National Institute of Information and Communications Technology"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018533235","display_name":"Yamato Ohtani","orcid":"https://orcid.org/0009-0009-2961-2821"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yamato Ohtani","raw_affiliation_strings":["National Institute of Information and Communications Technology"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132826845","display_name":"Tomoki Toda","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["National Institute of Information and Communications Technology"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132811394","display_name":"Hisashi Kawai","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","raw_affiliation_strings":["National Institute of Information and Communications Technology"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5082349516"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":2.1819,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92938148,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.8680999875068665,"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":0.8680999875068665,"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/T10730","display_name":"Language Development and Disorders","score":0.019700000062584877,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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/T10860","display_name":"Speech and Audio Processing","score":0.01889999955892563,"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/generalization","display_name":"Generalization","score":0.7190999984741211},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5873000025749207},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5723000168800354},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4221999943256378},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38100001215934753},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.34940001368522644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688999772071838},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7190999984741211},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5873000025749207},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5873000025749207},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5842999815940857},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5723000168800354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5579000115394592},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4221999943256378},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.34940001368522644},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3174000084400177},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2734000086784363},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434769","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":[{"display_name":"Quality Education","score":0.6030155420303345,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2084534958","https://openalex.org/W2107860279","https://openalex.org/W2183341477","https://openalex.org/W2519091744","https://openalex.org/W2526050071","https://openalex.org/W2963522141","https://openalex.org/W2964243274","https://openalex.org/W2972478942","https://openalex.org/W2972802841","https://openalex.org/W3095410713","https://openalex.org/W3097206152","https://openalex.org/W3196225973","https://openalex.org/W3198429080","https://openalex.org/W3202278141","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4224612669","https://openalex.org/W4225956675","https://openalex.org/W4226380987","https://openalex.org/W4296070211","https://openalex.org/W4297570641","https://openalex.org/W4372259881","https://openalex.org/W4372260534","https://openalex.org/W4385993869","https://openalex.org/W4391021560","https://openalex.org/W4392902957","https://openalex.org/W4393859250","https://openalex.org/W4395958010","https://openalex.org/W4401609230","https://openalex.org/W4402111350","https://openalex.org/W4402112072","https://openalex.org/W4402112143","https://openalex.org/W4402301063","https://openalex.org/W4402981815","https://openalex.org/W4403363072","https://openalex.org/W4404160901","https://openalex.org/W4405270664","https://openalex.org/W4406461865","https://openalex.org/W4406462026"],"related_works":[],"abstract_inverted_index":{"While":[0],"supervised":[1],"quality":[2,72,118],"predictors":[3],"for":[4,16],"synthesized":[5,108],"speech":[6,40,59,71,87],"have":[7],"demonstrated":[8],"strong":[9],"correlations":[10,103],"with":[11,104],"human":[12,105],"ratings,":[13],"their":[14,22],"requirement":[15],"in-domain":[17],"labeled":[18],"training":[19],"data":[20],"hinders":[21],"generalization":[23],"ability":[24],"to":[25],"new":[26],"domains.":[27],"Unsupervised":[28],"approaches":[29],"based":[30,36,89],"on":[31,90],"pretrained":[32,86],"self-supervised":[33],"learning":[34],"(SSL)":[35],"models":[37,43,55,88,115],"and":[38,110],"automatic":[39],"recognition":[41],"(ASR)":[42],"are":[44,73],"a":[45,76,81],"promising":[46],"alternative;":[47],"however,":[48],"little":[49],"is":[50],"known":[51],"about":[52,58],"how":[53,67],"these":[54],"encode":[56],"information":[57],"quality.":[60],"Towards":[61],"the":[62,129],"goal":[63],"of":[64,70,84,107,113,119,131],"better":[65],"understanding":[66],"different":[68],"aspects":[69],"encoded":[74],"in":[75],"multilingual":[77,85],"setting,":[78],"we":[79],"present":[80],"layer-wise":[82],"analysis":[83],"reference":[91,134],"modeling.":[92],"We":[93,126],"find":[94],"that":[95],"features":[96],"extracted":[97],"from":[98],"early":[99],"SSL":[100],"layers":[101,112],"show":[102],"ratings":[106],"speech,":[109],"later":[111],"ASR":[114],"can":[116],"predict":[117],"non-neural":[120],"systems":[121],"as":[122,124],"well":[123],"intelligibility.":[125],"also":[127],"demonstrate":[128],"importance":[130],"using":[132],"well-matched":[133],"data.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}