{"id":"https://openalex.org/W7148318761","doi":"https://doi.org/10.1109/asru65441.2025.11434779","title":"KyotoMOS2: MOS Prediction for Speech Across Multiple Sampling Rates","display_name":"KyotoMOS2: MOS Prediction for Speech Across Multiple Sampling Rates","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148318761","doi":"https://doi.org/10.1109/asru65441.2025.11434779"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434779","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Wangjin Zhou","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643391","display_name":"Yizhou Zhang","orcid":"https://orcid.org/0000-0002-8206-4694"},"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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yizhou Zhang","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009991655","display_name":"Keisuke Imoto","orcid":"https://orcid.org/0000-0002-0703-8293"},"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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Imoto","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132793867","display_name":"Tatsuya Kawahara","orcid":null},"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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032740716"],"corresponding_institution_ids":["https://openalex.org/I22299242","https://openalex.org/I39012071"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87552443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7123000025749207,"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":0.7123000025749207,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.054099999368190765,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.037300001829862595,"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/sampling","display_name":"Sampling (signal processing)","score":0.47360000014305115},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3440999984741211},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.25940001010894775},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.24469999969005585}],"concepts":[{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.47360000014305115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4668000042438507},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.35010001063346863},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3440999984741211},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3431999981403351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.314300000667572},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27079999446868896},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24469999969005585},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2354000061750412}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434779","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":12,"referenced_works":["https://openalex.org/W3198270377","https://openalex.org/W3202278141","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4223503417","https://openalex.org/W4225956675","https://openalex.org/W4296068974","https://openalex.org/W4372266552","https://openalex.org/W4390451904","https://openalex.org/W4391021560","https://openalex.org/W4393859250","https://openalex.org/W4406461503"],"related_works":[],"abstract_inverted_index":{"We":[0,16],"propose":[1],"KyotoMOS2,":[2],"an":[3],"automatic":[4],"MOS":[5],"prediction":[6],"system":[7,62],"capable":[8],"of":[9],"evaluating":[10],"speech":[11],"across":[12],"varying":[13],"sampling":[14],"rates.":[15],"design":[17],"a":[18],"sampling-rate-aware":[19],"SSL-MOS":[20],"subsystem":[21],"and":[22,29,36,42],"evaluate":[23],"32":[24],"variants":[25],"on":[26,33,66],"both":[27],"original":[28],"resampled":[30],"audio.":[31],"Based":[32],"system-level":[34,49],"SRCC":[35,67],"MSE,":[37],"13":[38],"subsystems":[39],"are":[40],"selected":[41],"fused":[43],"for":[44],"the":[45,58,69],"final":[46],"prediction.":[47],"A":[48],"SRCC-based":[50],"early":[51],"stopping":[52],"strategy":[53],"is":[54],"used":[55],"to":[56],"train":[57],"fusion":[59],"model.":[60],"Our":[61],"(T13)":[63],"ranked":[64],"2nd":[65],"in":[68],"AudioMOS":[70],"Track":[71],"3.":[72]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}