{"id":"https://openalex.org/W4402402459","doi":"https://doi.org/10.1109/ialp63756.2024.10661179","title":"Multi-Perspective Transfer Learning for Automatic MOS Prediction of Low Resource Language","display_name":"Multi-Perspective Transfer Learning for Automatic MOS Prediction of Low Resource Language","publication_year":2024,"publication_date":"2024-08-04","ids":{"openalex":"https://openalex.org/W4402402459","doi":"https://doi.org/10.1109/ialp63756.2024.10661179"},"language":"en","primary_location":{"id":"doi:10.1109/ialp63756.2024.10661179","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ialp63756.2024.10661179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Asian Language Processing (IALP)","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/A5072602270","display_name":"Pengkai Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengkai Yin","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448352","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0001-7254-9439"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Liu","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014372166","display_name":"Feilong Bao","orcid":"https://orcid.org/0000-0001-7312-1629"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feilong Bao","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"286","last_page":"290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9965000152587891,"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/T12031","display_name":"Speech and dialogue systems","score":0.9750999808311462,"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":0.7027589678764343},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6748561859130859},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6428347826004028},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4865330755710602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38520142436027527},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35509976744651794}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7027589678764343},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6748561859130859},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6428347826004028},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4865330755710602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38520142436027527},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35509976744651794},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp63756.2024.10661179","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ialp63756.2024.10661179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335581","display_name":"Young Scientists Fund","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2008924408","https://openalex.org/W2107860279","https://openalex.org/W2395579298","https://openalex.org/W2473388484","https://openalex.org/W2896457183","https://openalex.org/W2913954081","https://openalex.org/W2963035245","https://openalex.org/W2972394484","https://openalex.org/W2982223350","https://openalex.org/W3026777299","https://openalex.org/W3106690208","https://openalex.org/W3161558238","https://openalex.org/W3202278141","https://openalex.org/W3207932315","https://openalex.org/W4281492411","https://openalex.org/W4283730838","https://openalex.org/W4372259881","https://openalex.org/W4385245566","https://openalex.org/W4385822828","https://openalex.org/W4386041148","https://openalex.org/W4386058738","https://openalex.org/W4395959004","https://openalex.org/W6631190155","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6839074426"],"related_works":["https://openalex.org/W2149537132","https://openalex.org/W2018871932","https://openalex.org/W641279757","https://openalex.org/W370975646","https://openalex.org/W1670566515","https://openalex.org/W4242022592","https://openalex.org/W596972243","https://openalex.org/W4313230280","https://openalex.org/W3123837699","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Mean":[0],"Opinion":[1],"Score":[2],"(MOS)":[3],"prediction":[4,26,49,77],"is":[5,45],"the":[6,53,91,104,108,111,122],"task":[7],"to":[8,36,87,94],"automatically":[9],"evaluate":[10],"synthesized":[11],"speech":[12],"by":[13],"a":[14,19,63,72],"neural":[15],"network":[16],"that":[17,51,107],"emulates":[18],"human":[20],"listening":[21],"test.":[22],"Traditional":[23],"automatic":[24],"MOS":[25,48,76],"typically":[27],"focused":[28],"on":[29,103],"mainstream":[30,92],"languages,":[31,43],"such":[32],"as":[33],"English,":[34],"due":[35],"large":[37],"available":[38],"data.":[39],"However,":[40],"for":[41],"low-resource":[42,95],"there":[44],"no":[46],"large-scale":[47],"data,":[50],"hinders":[52],"study":[54],"of":[55],"those":[56],"languages.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61],"propose":[62],"novel":[64],"Multi-Perspective":[65],"Transfer":[66,83,86],"Learning":[67],"(MPTL)":[68],"training":[69,114],"scheme":[70,115],"with":[71,116],"new":[73],"small-scale":[74],"Mongolian":[75],"dataset":[78,127],"MonMOS.":[79],"MPTL":[80,109],"includes":[81],"Feature":[82],"and":[84,125],"Model":[85],"transfer":[88],"knowledge":[89],"from":[90,97],"languages":[93],"language":[96],"different":[98],"perspectives.":[99],"The":[100],"experimental":[101],"results":[102],"MonMOS":[105,126],"show":[106],"outperforms":[110],"standard":[112],"direct":[113],"classical":[117],"architecture.":[118],"We":[119],"will":[120],"release":[121],"pre-trained":[123],"models":[124],"at:":[128],"https://github.com/Ai-S2-Lab/MPTL-MOS.":[129]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}