{"id":"https://openalex.org/W4391021229","doi":"https://doi.org/10.1109/asru57964.2023.10389797","title":"Partial Rank Similarity Minimization Method for Quality MOS Prediction of Unseen Speech Synthesis Systems in Zero-Shot and Semi-Supervised Setting","display_name":"Partial Rank Similarity Minimization Method for Quality MOS Prediction of Unseen Speech Synthesis Systems in Zero-Shot and Semi-Supervised Setting","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021229","doi":"https://doi.org/10.1109/asru57964.2023.10389797"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389797","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389797","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/A5003400894","display_name":"Hemant Yadav","orcid":"https://orcid.org/0000-0003-3057-1456"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hemant Yadav","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082349516","display_name":"Erica Cooper","orcid":"https://orcid.org/0000-0002-2978-2793"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erica Cooper","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005513786","display_name":"Sunayana Sitaram","orcid":"https://orcid.org/0000-0003-4251-9719"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sunayana Sitaram","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079357056","display_name":"Rajiv Ratn Shah","orcid":"https://orcid.org/0000-0003-1028-9373"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajiv Ratn Shah","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003400894"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59613534,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"56","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":0.9998999834060669,"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":0.9977999925613403,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9884999990463257,"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/zero","display_name":"Zero (linguistics)","score":0.6589189767837524},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.643488347530365},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6413605213165283},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6314697861671448},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6230577826499939},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5741056203842163},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5372028350830078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5077642202377319},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.46421125531196594},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42137324810028076},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4125713109970093},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33253729343414307},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28844988346099854},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13477668166160583}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6589189767837524},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.643488347530365},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6413605213165283},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6314697861671448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6230577826499939},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5741056203842163},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5372028350830078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5077642202377319},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46421125531196594},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42137324810028076},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4125713109970093},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33253729343414307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28844988346099854},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13477668166160583},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389797","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389797","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320327550","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1523817494","https://openalex.org/W1595709623","https://openalex.org/W2101105183","https://openalex.org/W2587275078","https://openalex.org/W2592497314","https://openalex.org/W2963522141","https://openalex.org/W2972394484","https://openalex.org/W3024752295","https://openalex.org/W3026777299","https://openalex.org/W3034238904","https://openalex.org/W3036601975","https://openalex.org/W3161558238","https://openalex.org/W3196225973","https://openalex.org/W3202278141","https://openalex.org/W4225956675","https://openalex.org/W4296068974","https://openalex.org/W4296070386","https://openalex.org/W6635459924","https://openalex.org/W6780218876","https://openalex.org/W6865530009"],"related_works":["https://openalex.org/W4214877189","https://openalex.org/W2074502265","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2366718574","https://openalex.org/W2370553949","https://openalex.org/W4297833975","https://openalex.org/W2934154379","https://openalex.org/W2052067742","https://openalex.org/W2953384352"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,33,133],"novel":[4],"objective":[5],"function":[6,21],"for":[7,121,136,143],"quality":[8,139],"mean":[9,110],"opinion":[10],"score":[11],"(MOS)":[12],"prediction":[13,104,124],"of":[14,25,28,93],"unseen":[15],"speech":[16,65,138,146],"synthesis":[17,66,147],"systems.":[18,148],"The":[19],"proposed":[20],"measures":[22],"the":[23,37,43,52,58,70,91],"similarity":[24,46],"relative":[26],"positions":[27],"predicted":[29],"MOS":[30,39,54,103,123],"values,":[31],"in":[32,77],"mini-batch,":[34],"rather":[35,50],"than":[36,51],"actual":[38],"values.":[40],"That":[41],"is":[42,47],"partial":[44],"rank":[45,95],"measured":[48],"$(\\mathcal{P}RS)$":[49],"individual":[53],"values":[55],"as":[56,97],"with":[57,85],"L1":[59,75],"loss.":[60],"Our":[61],"experiments":[62],"on":[63],"out-of-domain":[64],"systems":[67],"demonstrate":[68],"that":[69,109],"$\\mathcal{P}":[71,128],"R":[72,129],"S$":[73],"outperforms":[74],"loss":[76],"zero-shot":[78],"and":[79,113,140,150],"semi-supervised":[80],"settings,":[81],"exhibiting":[82],"stronger":[83],"correlation":[84,115],"ground":[86],"truth.":[87],"These":[88],"findings":[89],"highlight":[90],"importance":[92],"considering":[94],"order,":[96],"done":[98],"by":[99],"$\\mathcal{P}RS$,":[100],"when":[101],"training":[102],"models.":[105,125],"We":[106],"also":[107],"argue":[108],"squared":[111],"error":[112],"linear":[114],"coefficient":[116],"metrics":[117],"may":[118],"be":[119],"unreliable":[120],"evaluating":[122,137],"In":[126],"conclusion,":[127],"S$-trained":[130],"models":[131,151],"provide":[132],"robust":[134],"framework":[135],"offer":[141],"insights":[142],"developing":[144],"high-quality":[145],"Code":[149],"are":[152],"available":[153],"at":[154],"github.com/nii-yamagishilab/partial_rank_similarity/":[155]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}