{"id":"https://openalex.org/W4225319489","doi":"https://doi.org/10.1109/icassp43922.2022.9747533","title":"MOS Predictor for Synthetic Speech with I-Vector Inputs","display_name":"MOS Predictor for Synthetic Speech with I-Vector Inputs","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225319489","doi":"https://doi.org/10.1109/icassp43922.2022.9747533"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747533","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100348904","display_name":"Miao Liu","orcid":"https://orcid.org/0000-0002-6650-9972"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miao Liu","raw_affiliation_strings":["Beijing Institute of Technology,Beijing,China","Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378420","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0002-0245-1986"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["Beijing Institute of Technology,Beijing,China","Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030965527","display_name":"Shicong Li","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shicong Li","raw_affiliation_strings":["Xiaomi Inc,Beijing,China","Xiaomi Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Inc, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090837004","display_name":"Fei Xiang","orcid":"https://orcid.org/0000-0003-3644-7114"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Xiang","raw_affiliation_strings":["Xiaomi Inc,Beijing,China","Xiaomi Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Inc, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102287479","display_name":"Yue Yao","orcid":"https://orcid.org/0009-0001-9509-8199"},"institutions":[{"id":"https://openalex.org/I31637741","display_name":"Inner Mongolia University of Science and Technology","ror":"https://ror.org/044rgx723","country_code":"CN","type":"education","lineage":["https://openalex.org/I31637741"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Yao","raw_affiliation_strings":["Inner Mongolia University of Science and Technology,Baotou,China","Inner Mongolia University of Science and Technology, Baotou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University of Science and Technology,Baotou,China","institution_ids":["https://openalex.org/I31637741"]},{"raw_affiliation_string":"Inner Mongolia University of Science and Technology, Baotou, China","institution_ids":["https://openalex.org/I31637741"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112688917","display_name":"Lidong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I31637741","display_name":"Inner Mongolia University of Science and Technology","ror":"https://ror.org/044rgx723","country_code":"CN","type":"education","lineage":["https://openalex.org/I31637741"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lidong Yang","raw_affiliation_strings":["Inner Mongolia University of Science and Technology,Baotou,China","Inner Mongolia University of Science and Technology, Baotou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University of Science and Technology,Baotou,China","institution_ids":["https://openalex.org/I31637741"]},{"raw_affiliation_string":"Inner Mongolia University of Science and Technology, Baotou, China","institution_ids":["https://openalex.org/I31637741"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"906","last_page":"910"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7909586429595947},{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.6833895444869995},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6775673627853394},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.626215934753418},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5368097424507141},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5233408808708191},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5219254493713379},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5150399208068848},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4987375736236572},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4582618176937103},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4510672092437744},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4157387912273407},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08748519420623779}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7909586429595947},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.6833895444869995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6775673627853394},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.626215934753418},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5368097424507141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5233408808708191},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5219254493713379},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5150399208068848},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4987375736236572},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4582618176937103},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4510672092437744},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4157387912273407},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08748519420623779},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747533","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"ICASSP 2022 - 2022 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","display_name":"Quality Education","score":0.7699999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1985371235","https://openalex.org/W2075843680","https://openalex.org/W2107638917","https://openalex.org/W2150769028","https://openalex.org/W2293442930","https://openalex.org/W2407501792","https://openalex.org/W2473388484","https://openalex.org/W2515667479","https://openalex.org/W2519091744","https://openalex.org/W2557915412","https://openalex.org/W2774848319","https://openalex.org/W2922332774","https://openalex.org/W2945478979","https://openalex.org/W2963035245","https://openalex.org/W2963403924","https://openalex.org/W2964243274","https://openalex.org/W2972394484","https://openalex.org/W3036655771","https://openalex.org/W3047992192","https://openalex.org/W3097206152","https://openalex.org/W3147454823","https://openalex.org/W3161558238","https://openalex.org/W3196475561","https://openalex.org/W4292402161","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6729924827","https://openalex.org/W6739901393","https://openalex.org/W6746801104","https://openalex.org/W6762533536","https://openalex.org/W6780855921"],"related_works":["https://openalex.org/W2064370490","https://openalex.org/W3166813893","https://openalex.org/W2910013580","https://openalex.org/W2391900574","https://openalex.org/W2362773009","https://openalex.org/W2169113179","https://openalex.org/W1564107245","https://openalex.org/W2295649751","https://openalex.org/W3016124757","https://openalex.org/W3034520363"],"abstract_inverted_index":{"Based":[0],"on":[1,71,97,138],"deep":[2,61],"learning":[3],"technology,":[4],"non-intrusive":[5],"methods":[6],"have":[7,43],"received":[8],"increasing":[9],"attention":[10],"for":[11],"synthetic":[12,118],"speech":[13,31,48,119],"quality":[14,116],"assessment":[15],"since":[16],"it":[17,45],"does":[18],"not":[19],"need":[20],"reference":[21],"signals.":[22],"Meanwhile,":[23],"i-vector":[24,70,109,126],"has":[25],"been":[26],"widely":[27],"used":[28,44],"in":[29],"paralinguistic":[30],"attribute":[32],"recognition":[33],"such":[34],"as":[35,79],"speaker":[36],"and":[37,69,75,94,103,120,127,136,141],"emotion":[38],"recognition,":[39],"but":[40],"few":[41],"studies":[42],"to":[46,114],"estimate":[47],"quality.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,88],"propose":[54],"a":[55],"neural-network-based":[56],"model":[57],"that":[58,108,124],"splices":[59],"the":[60,72,85,90,115,121,132],"features":[62],"extracted":[63],"by":[64],"convolutional":[65],"neural":[66],"network":[67],"(CNN)":[68],"time":[73,80],"axis":[74],"uses":[76],"Transformer":[77,128],"encoder":[78,129],"sequence":[81],"model.":[82],"To":[83],"evaluate":[84],"proposed":[86,122],"method,":[87],"improve":[89],"previous":[91],"prediction":[92],"models":[93,123],"conduct":[95],"experiments":[96],"Voice":[98],"Conversion":[99],"Challenge":[100],"(VCC)":[101],"2018":[102],"2016":[104],"dataset.":[105],"Results":[106],"show":[107],"contains":[110],"information":[111],"very":[112],"related":[113],"of":[117,134],"utilize":[125],"highly":[130],"increase":[131],"accuracy":[133],"MOSNet":[135],"MBNet":[137],"both":[139],"utterance-level":[140],"system-level":[142],"results.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}