{"id":"https://openalex.org/W4408353910","doi":"https://doi.org/10.1109/icassp49660.2025.10887675","title":"Rethinking Mean Opinion Scores in Speech Quality Assessment: Score Aggregation through Quantized Distribution Fitting","display_name":"Rethinking Mean Opinion Scores in Speech Quality Assessment: Score Aggregation through Quantized Distribution Fitting","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353910","doi":"https://doi.org/10.1109/icassp49660.2025.10887675"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5054416087","display_name":"Yuto Kondo","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuto Kondo","raw_affiliation_strings":["NTT Corporation,Communication Science Laboratories,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Communication Science Laboratories,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001243214","display_name":"Hirokazu Kameoka","orcid":"https://orcid.org/0000-0003-3102-0162"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirokazu Kameoka","raw_affiliation_strings":["NTT Corporation,Communication Science Laboratories,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Communication Science Laboratories,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106710403","display_name":"Kou Tanaka","orcid":"https://orcid.org/0009-0003-7107-607X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kou Tanaka","raw_affiliation_strings":["NTT Corporation,Communication Science Laboratories,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Communication Science Laboratories,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020693766","display_name":"Takuhiro Kaneko","orcid":"https://orcid.org/0009-0000-8016-5144"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuhiro Kaneko","raw_affiliation_strings":["NTT Corporation,Communication Science Laboratories,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Communication Science Laboratories,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054416087"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":2.5656,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86006884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11871","display_name":"Advanced Statistical Methods and Models","score":0.7404999732971191,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11871","display_name":"Advanced Statistical Methods and Models","score":0.7404999732971191,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.7190138101577759},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.520433247089386},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.4997086524963379},{"id":"https://openalex.org/keywords/quality-assessment","display_name":"Quality assessment","score":0.4914740324020386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4879102408885956},{"id":"https://openalex.org/keywords/quality-score","display_name":"Quality Score","score":0.44229796528816223},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3735330104827881},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35385066270828247},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3220023512840271},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24574553966522217},{"id":"https://openalex.org/keywords/evaluation-methods","display_name":"Evaluation methods","score":0.12769848108291626},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11200293898582458},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06676062941551208},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.06333383917808533}],"concepts":[{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.7190138101577759},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.520433247089386},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4997086524963379},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.4914740324020386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4879102408885956},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.44229796528816223},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3735330104827881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35385066270828247},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3220023512840271},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24574553966522217},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.12769848108291626},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11200293898582458},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06676062941551208},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.06333383917808533},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2075843680","https://openalex.org/W2972394484","https://openalex.org/W2972667718","https://openalex.org/W3161558238","https://openalex.org/W3196225973","https://openalex.org/W3202278141","https://openalex.org/W3207932315","https://openalex.org/W4225956675","https://openalex.org/W4296068974","https://openalex.org/W4299959846","https://openalex.org/W4363650269","https://openalex.org/W4385822527","https://openalex.org/W4385822628","https://openalex.org/W4392909620","https://openalex.org/W4393859250","https://openalex.org/W4402111227","https://openalex.org/W4402111503","https://openalex.org/W4404577414","https://openalex.org/W6683600756","https://openalex.org/W6729924827","https://openalex.org/W6762533536","https://openalex.org/W6778823374","https://openalex.org/W6795261426","https://openalex.org/W6796464841","https://openalex.org/W6802527329","https://openalex.org/W7005955626"],"related_works":["https://openalex.org/W2033549879","https://openalex.org/W2013629269","https://openalex.org/W2096935541","https://openalex.org/W4221158116","https://openalex.org/W2943685190","https://openalex.org/W4391020683","https://openalex.org/W3027116454","https://openalex.org/W2986204340","https://openalex.org/W3047188278","https://openalex.org/W1967325901"],"abstract_inverted_index":{"This":[0],"study":[1],"addresses":[2],"the":[3,15,32,51,54,68,90,100,105,112,115,120,123,129],"task":[4],"of":[5,18,37,53,62,70,114,133],"speech":[6,38],"quality":[7,17],"assessment":[8],"(SQA),":[9],"which":[10],"aims":[11],"to":[12,30,49],"automatically":[13],"predict":[14,31],"subjective":[16],"a":[19,57],"given":[20],"speech.":[21],"Recent":[22],"efforts":[23],"have":[24],"focused":[25],"on":[26],"training":[27],"neural-based":[28],"models":[29,55],"mean":[33],"opinion":[34],"score":[35,58],"(MOS)":[36],"samples":[39],"produced":[40],"by":[41,56,77,103],"text-to-speech":[42],"or":[43],"voice":[44],"conversion":[45],"systems.":[46],"We":[47,109],"aim":[48],"enhance":[50],"performance":[52],"aggregation":[59],"method":[60,66,81],"instead":[61,132],"MOS.":[63,134],"The":[64],"proposed":[65,144],"mitigates":[67],"effects":[69],"some":[71],"issues":[72],"arising":[73],"from":[74],"constraints":[75],"imposed":[76],"limited":[78],"options.":[79],"Our":[80],"assumes":[82],"annotators":[83],"internally":[84],"consider":[85],"continuous":[86,107],"scores":[87],"and":[88,125],"pick":[89],"nearest":[91],"discrete":[92],"rating.":[93],"By":[94],"modeling":[95],"this":[96,143],"process,":[97],"we":[98],"approximate":[99],"rating":[101],"distribution":[102,124],"quantizing":[104],"latent":[106,116],"distribution.":[108],"then":[110],"use":[111],"peak":[113],"distribution,":[117],"estimated":[118],"through":[119],"loss":[121],"between":[122],"actual":[126],"ratings,":[127],"as":[128],"new":[130],"value":[131,145],"Experimental":[135],"results":[136],"demonstrate":[137],"that":[138],"substituting":[139],"MOSNet\u2019s":[140],"target":[141],"with":[142],"improves":[146],"prediction":[147],"performance.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}