{"id":"https://openalex.org/W4391021629","doi":"https://doi.org/10.1109/asru57964.2023.10389788","title":"LE-SSL-MOS: Self-Supervised Learning MOS Prediction with Listener Enhancement","display_name":"LE-SSL-MOS: Self-Supervised Learning MOS Prediction with Listener Enhancement","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021629","doi":"https://doi.org/10.1109/asru57964.2023.10389788"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5108894901","display_name":"Zili Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zili Qi","raw_affiliation_strings":["Hithink RoyalFlush AI Research Institute,Zhejiang,China","Hithink RoyalFlush AI Research Institute, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute,Zhejiang,China","institution_ids":[]},{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute, Zhejiang, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013876048","display_name":"Xinhui Hu","orcid":"https://orcid.org/0009-0009-1433-9324"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinhui Hu","raw_affiliation_strings":["Hithink RoyalFlush AI Research Institute,Zhejiang,China","Hithink RoyalFlush AI Research Institute, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute,Zhejiang,China","institution_ids":[]},{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute, Zhejiang, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032740716","display_name":"Wangjin Zhou","orcid":"https://orcid.org/0009-0007-0693-5316"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wangjin Zhou","raw_affiliation_strings":["Kyoto University,Kyoto,Japan","Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University,Kyoto,Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"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":"Sheng Li","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT),Kyoto,Japan","National Institute of Information and Communications Technology (NICT), Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT),Kyoto,Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102872175","display_name":"Hao Wu","orcid":"https://orcid.org/0000-0002-5618-4887"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Wu","raw_affiliation_strings":["Hithink RoyalFlush AI Research Institute,Zhejiang,China","Hithink RoyalFlush AI Research Institute, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute,Zhejiang,China","institution_ids":[]},{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute, Zhejiang, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089831591","display_name":"Jian L\u00fc","orcid":"https://orcid.org/0000-0002-9144-7486"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Lu","raw_affiliation_strings":["Hithink RoyalFlush AI Research Institute,Zhejiang,China","Hithink RoyalFlush AI Research Institute, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute,Zhejiang,China","institution_ids":[]},{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute, Zhejiang, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000141731","display_name":"Xinkang Xu","orcid":"https://orcid.org/0009-0003-2771-1398"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinkang Xu","raw_affiliation_strings":["Hithink RoyalFlush AI Research Institute,Zhejiang,China","Hithink RoyalFlush AI Research Institute, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute,Zhejiang,China","institution_ids":[]},{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute, Zhejiang, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5108894901"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2575,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90678966,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9940999746322632,"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/T12031","display_name":"Speech and dialogue systems","score":0.9901999831199646,"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/computer-science","display_name":"Computer science","score":0.7963255643844604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6539314985275269},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6046770811080933},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.48468998074531555},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4843805730342865},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4526592791080475},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45007920265197754},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.43339425325393677},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3579038977622986},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3375096917152405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7963255643844604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6539314985275269},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6046770811080933},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.48468998074531555},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4843805730342865},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4526592791080475},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45007920265197754},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.43339425325393677},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3579038977622986},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3375096917152405},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru57964.2023.10389788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50729886","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100931489","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2933138175","https://openalex.org/W2972394484","https://openalex.org/W3148101939","https://openalex.org/W3161558238","https://openalex.org/W3202278141","https://openalex.org/W3207932315","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4223503417","https://openalex.org/W4225956675","https://openalex.org/W4226198268","https://openalex.org/W4296068818","https://openalex.org/W4296068832","https://openalex.org/W4296068974","https://openalex.org/W4296070386","https://openalex.org/W4297570641","https://openalex.org/W4297841508","https://openalex.org/W4322714819","https://openalex.org/W4372259881","https://openalex.org/W6780218876","https://openalex.org/W6802255848","https://openalex.org/W6844194202","https://openalex.org/W6847767607","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W3148060700","https://openalex.org/W3080681248","https://openalex.org/W4376646226","https://openalex.org/W3047177827","https://openalex.org/W4287685660","https://openalex.org/W2057778272","https://openalex.org/W4319302697","https://openalex.org/W2986085304","https://openalex.org/W2163389298","https://openalex.org/W205223620"],"abstract_inverted_index":{"Recently,":[0],"researchers":[1],"have":[2],"shown":[3],"an":[4,110,173],"increasing":[5],"interest":[6],"in":[7,79,197],"automatically":[8],"predicting":[9],"the":[10,25,49,73,80,85,107,126,132,139,157,167,182,198,204,211],"subjective":[11],"evaluation":[12],"for":[13,38,148],"speech":[14,186,200,208],"synthesis":[15,201],"systems.":[16],"This":[17],"prediction":[18,40,69],"is":[19,93,115,138],"a":[20,34,54,122],"challenging":[21],"task,":[22],"especially":[23],"on":[24,156,181],"out-of-domain":[26],"test":[27],"set.":[28],"In":[29,48,84],"this":[30,137],"paper,":[31],"we":[32,52,95,117],"proposed":[33],"novel":[35],"fusion":[36,170],"model":[37,99],"MOS":[39,149],"that":[41,94,116,142,162],"combines":[42],"both":[43],"supervised":[44,50,144],"and":[45,66,145,184,193,203,206],"unsupervised":[46,86,111,146],"approaches.":[47],"aspect,":[51,87],"developed":[53],"SSL-based":[55],"predictor":[56],"called":[57],"LE-SSL-MOS.":[58],"The":[59],"LE-SSL-MOS":[60,163,180],"utilizes":[61],"pre-trained":[62],"self-supervised":[63],"learning":[64],"models":[65],"further":[67],"improves":[68],"accuracy":[70],"by":[71],"utilizing":[72],"opinion":[74],"scores":[75],"of":[76,109,128,134,176,210],"each":[77],"utterance":[78],"listener":[81],"enhancement":[82],"branch.":[83],"two":[88],"steps":[89],"are":[90],"contained:":[91],"one":[92],"fine-tuned":[96],"unit":[97],"language":[98],"(ULM)":[100],"using":[101],"highly-intelligible":[102],"domain":[103],"data":[104],"to":[105],"improve":[106],"correlation":[108],"metric":[112,124],"SpeechLMScore.":[113],"Another":[114],"utilized":[118],"ASR":[119],"confidence":[120],"as":[121],"new":[123],"with":[125],"help":[127],"ensemble":[129],"learning.":[130],"To":[131],"best":[133],"our":[135,153,189],"knowledge,":[136],"first":[140],"architecture":[141],"fuses":[143],"methods":[147],"prediction.With":[150],"these":[151],"approaches,":[152],"experimental":[154],"results":[155],"VoiceMOS":[158],"Challenge":[159],"2023":[160],"show":[161],"performs":[164],"better":[165],"than":[166],"baseline.":[168],"Our":[169],"system":[171,190],"achieved":[172],"absolute":[174],"improvement":[175],"13":[177],"%":[178],"over":[179],"noisy":[183,205],"enhanced":[185,207],"track.":[187],"And":[188],"ranked":[191],"1st":[192],"2":[194],"nd":[195],"respectively":[196],"French":[199],"track":[202,209],"challenge.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}