{"id":"https://openalex.org/W4385823430","doi":"https://doi.org/10.21437/interspeech.2023-589","title":"Preference-based training framework for automatic speech quality assessment using deep neural network","display_name":"Preference-based training framework for automatic speech quality assessment using deep neural network","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823430","doi":"https://doi.org/10.21437/interspeech.2023-589"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-589","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.15203","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071175201","display_name":"Cheng-Hung Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Cheng-Hung Hu","raw_affiliation_strings":["Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068072475","display_name":"Yusuke Yasuda","orcid":"https://orcid.org/0000-0002-2130-747X"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Yasuda","raw_affiliation_strings":["Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4895,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70790145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"546","last_page":"550"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9987000226974487,"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/T11309","display_name":"Music and Audio Processing","score":0.9932000041007996,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7962008714675903},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6897339224815369},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.6858857870101929},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.6340059638023376},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5752268433570862},{"id":"https://openalex.org/keywords/spearmans-rank-correlation-coefficient","display_name":"Spearman's rank correlation coefficient","score":0.5720593929290771},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5677700042724609},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5611163973808289},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5361815094947815},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5102581977844238},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4988281726837158},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4200096130371094},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39801108837127686},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.28663527965545654},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16798114776611328},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0742134153842926}],"concepts":[{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7962008714675903},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6897339224815369},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.6858857870101929},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6340059638023376},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5752268433570862},{"id":"https://openalex.org/C159744936","wikidata":"https://www.wikidata.org/wiki/Q1126730","display_name":"Spearman's rank correlation coefficient","level":2,"score":0.5720593929290771},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5677700042724609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5611163973808289},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5361815094947815},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5102581977844238},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4988281726837158},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4200096130371094},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39801108837127686},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.28663527965545654},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16798114776611328},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0742134153842926},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-589","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.15203","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.15203","pdf_url":"https://arxiv.org/pdf/2308.15203","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.15203","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.15203","pdf_url":"https://arxiv.org/pdf/2308.15203","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.699999988079071,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G8892501299","display_name":null,"funder_award_id":"JPMJCR19A3","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385823430.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1275832873","https://openalex.org/W1522301498","https://openalex.org/W1552582326","https://openalex.org/W1673310716","https://openalex.org/W1728888090","https://openalex.org/W1976188834","https://openalex.org/W2249663999","https://openalex.org/W2763110165","https://openalex.org/W2935711438","https://openalex.org/W2963091184","https://openalex.org/W2972394484","https://openalex.org/W3026874504","https://openalex.org/W3036601975","https://openalex.org/W3128351426","https://openalex.org/W3161558238","https://openalex.org/W3172148458","https://openalex.org/W3200245256","https://openalex.org/W4224920010","https://openalex.org/W4225956675","https://openalex.org/W4294379402","https://openalex.org/W4297841766","https://openalex.org/W4300816538","https://openalex.org/W4322714819"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2214944207","https://openalex.org/W4312096575"],"abstract_inverted_index":{"One":[0],"objective":[1],"of":[2,12,52,74,88,106,127],"Speech":[3],"Quality":[4],"Assessment":[5],"(SQA)":[6],"is":[7,38,46],"to":[8,41,90,111,121],"estimate":[9,42],"the":[10,34,102,138],"ranks":[11],"synthetic":[13],"speech":[14,61],"systems.":[15,68],"However,":[16],"recent":[17],"SQA":[18,75],"models":[19,76],"are":[20],"typically":[21],"trained":[22,80],"using":[23],"low-precision":[24],"direct":[25],"scores":[26,31,51,84],"such":[27],"as":[28,33],"mean":[29],"opinion":[30],"(MOS)":[32],"training":[35,72],"objective,":[36],"which":[37],"not":[39,58],"straightforward":[40],"ranking.":[43],"Although":[44],"it":[45],"effective":[47],"for":[48,60],"predicting":[49],"quality":[50],"individual":[53],"sentences,":[54],"this":[55],"approach":[56],"does":[57],"account":[59],"and":[62,118],"system":[63,113],"preferences":[64],"when":[65],"ranking":[66,92],"multiple":[67],"We":[69],"propose":[70],"a":[71,125],"framework":[73,100],"that":[77,132],"can":[78],"be":[79],"with":[81],"only":[82],"preference":[83,123],"derived":[85],"from":[86,115,124],"pairs":[87],"MOS":[89],"improve":[91],"prediction.":[93],"Our":[94,129],"experiment":[95],"reveals":[96],"conditions":[97],"where":[98],"our":[99,133],"works":[101],"best":[103],"in":[104,141],"terms":[105],"pair":[107,126],"generation,":[108],"aggregation":[109],"functions":[110,120],"derive":[112],"score":[114],"utterance":[116],"preferences,":[117],"threshold":[119],"determine":[122],"MOS.":[128],"results":[130],"demonstrate":[131],"proposed":[134],"method":[135],"significantly":[136],"outperforms":[137],"baseline":[139],"model":[140],"Spearman's":[142],"Rank":[143],"Correlation":[144],"Coefficient.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}