{"id":"https://openalex.org/W4412944803","doi":"https://doi.org/10.18653/v1/2025.acl-long.1150","title":"QualiSpeech: A Speech Quality Assessment Dataset with Natural Language Reasoning and Descriptions","display_name":"QualiSpeech: A Speech Quality Assessment Dataset with Natural Language Reasoning and Descriptions","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944803","doi":"https://doi.org/10.18653/v1/2025.acl-long.1150"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1150","doi":"https://doi.org/10.18653/v1/2025.acl-long.1150","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1150","pdf_url":"https://aclanthology.org/2025.acl-long.1150.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2025.acl-long.1150.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017974335","display_name":"Siyin Wang","orcid":"https://orcid.org/0009-0008-7992-2476","observed_orcids":["https://orcid.org/0009-0008-7992-2476"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyin Wang","raw_affiliation_strings":["Tsinghua University , 2 ByteDance ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University , 2 ByteDance ,","institution_ids":["https://openalex.org/I4405256866","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109693003","display_name":"Wenyi Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyi Yu","raw_affiliation_strings":["Tsinghua University , 2 ByteDance ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University , 2 ByteDance ,","institution_ids":["https://openalex.org/I4405256866","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109692700","display_name":"Xianzhao Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianzhao Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100959470","display_name":"Xiaohai Tian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaohai Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433039","display_name":"Jun Zhang","orcid":"https://orcid.org/0000-0001-5441-3474","observed_orcids":["https://orcid.org/0000-0001-5441-3474"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100945425","display_name":"Lu Lu","orcid":"https://orcid.org/0000-0003-3328-118X","observed_orcids":["https://orcid.org/0000-0003-3328-118X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418","observed_orcids":["https://orcid.org/0000-0001-6956-0418"]},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Academia Sinica ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica ,","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955","observed_orcids":["https://orcid.org/0000-0003-2752-3955"]},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102687890","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0003-2489-6932","observed_orcids":["https://orcid.org/0000-0003-2489-6932"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075174215","display_name":"Chao Zhang","orcid":"https://orcid.org/0009-0008-8848-8085","observed_orcids":["https://orcid.org/0009-0008-8848-8085"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Tsinghua University , 2 ByteDance ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University , 2 ByteDance ,","institution_ids":["https://openalex.org/I4405256866","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.7482,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.95491299,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"23588","last_page":"23609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.88919997215271,"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":0.88919997215271,"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":0.0714000016450882,"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":0.013100000098347664,"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/speech-quality-assessment","display_name":"speech quality assessment","score":0.9929999709129333},{"id":"https://openalex.org/keywords/natural-language-reasoning","display_name":"natural language reasoning","score":0.8180000185966492},{"id":"https://openalex.org/keywords/subjective-quality-assessment","display_name":"subjective quality assessment","score":0.37400001287460327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8074758052825928},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6596817970275879},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6192799210548401},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.581932008266449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5100424885749817},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.5063430070877075},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.47332367300987244},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4729475677013397},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3582245707511902},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.10773292183876038},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05896839499473572},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1150","doi":"https://doi.org/10.18653/v1/2025.acl-long.1150","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1150","pdf_url":"https://aclanthology.org/2025.acl-long.1150.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.20290","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.20290","pdf_url":"https://arxiv.org/pdf/2503.20290","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.20290","doi":"https://doi.org/10.48550/arxiv.2503.20290","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.20290","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1150","doi":"https://doi.org/10.18653/v1/2025.acl-long.1150","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1150","pdf_url":"https://aclanthology.org/2025.acl-long.1150.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G8447728844","display_name":null,"funder_award_id":"62476151","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944803.pdf","grobid_xml":"https://content.openalex.org/works/W4412944803.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4408345667","https://openalex.org/W7092316554","https://openalex.org/W7114773363","https://openalex.org/W4406975147","https://openalex.org/W4415193852","https://openalex.org/W7155030520","https://openalex.org/W7135057827","https://openalex.org/W7204106467","https://openalex.org/W7125820872","https://openalex.org/W4414897574"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"a":[3,50,173],"novel":[4],"perspective":[5],"to":[6,77,120,207,241,276,321,353],"speech":[7,53,81],"quality":[8,54,127,346],"assessment":[9,55],"by":[10],"leveraging":[11],"natural":[12,63],"language":[13,25,64,87],"descriptions,":[14],"offering":[15],"richer,":[16],"more":[17],"nuanced":[18],"insights":[19],"than":[20],"traditional":[21],"numerical":[22],"scoring":[23],"methods.Natural":[24],"feedback":[26],"provides":[27],"instructive":[28],"recommendations":[29],"and":[30,61,69,103,109,124],"detailed":[31,62,99],"evaluations,":[32],"yet":[33],"existing":[34],"datasets":[35],"lack":[36],"the":[37,74,79,115,122,140,144,146,168,171,176,198,202,204,231,236,238,264,267,273,313,316,318,344,348,350,370],"comprehensive":[38,51],"annotations":[39],"needed":[40],"for":[41,117],"this":[42,45,374],"approach.To":[43],"bridge":[44],"gap,":[46],"we":[47,72],"introduce":[48],"QualiSpeech,":[49],"lowlevel":[52],"dataset":[56,129],"encompassing":[57],"11":[58],"key":[59],"aspects":[60],"comments":[65],"that":[66,92],"include":[67],"reasoning":[68,119],"contextual":[70],"insights.Additionally,":[71],"propose":[73],"QualiSpeech":[75],"Benchmark":[76],"evaluate":[78],"low-level":[80],"understanding":[82],"capabilities":[83],"of":[84,101,126,170,233,266,315,347],"auditory":[85,94],"large":[86],"models":[88],"(LLMs).Experimental":[89],"results":[90,112],"demonstrate":[91],"finetuned":[93],"LLMs":[95],"can":[96,130],"reliably":[97],"generate":[98],"descriptions":[100],"noise":[102,199,371],"distortion,":[104],"effectively":[105],"identifying":[106],"their":[107],"types":[108],"temporal":[110],"characteristics.The":[111],"further":[113],"highlight":[114],"potential":[116],"incorporating":[118],"enhance":[121],"accuracy":[123],"reliability":[125],"assessments.The":[128],"be":[131],"found":[132],"at":[133],"https://huggingface.co/":[134],"datasets/tsinghua-ee/QualiSpeech.":[135],"Speed:How":[136],"would":[137,165,195,228,261,310,341],"you":[138,166,196,229,262,269,311,342],"assess":[139],"speaking":[141],"speed":[142],"in":[143,201,235,373],"audio?Use":[145,203,237,317,349],"following":[147,177,205,239,274,319,351],"scale:":[148,178],"5.":[149,179,280,325,357],"Very":[150,162,180,192,225,257,326,338],"fast,":[151,154],"4.":[152,182,213,247,287,328,359],"Mostly":[153,183,329],"3.":[155,185,216,250,294,331,361],"Moderate":[156,295],"speed,":[157],"2.":[158,188,221,253,298,334,363],"Fairly":[159,189,254,335],"slow,":[160],"1.":[161,191,224,256,337,365],"slow.":[163],"Naturalness:How":[164],"rate":[167,197,230,263,312,343],"naturalness":[169],"audio?Choose":[172],"number":[174],"from":[175],"natural,":[181,184,187],"Somewhat":[186,222,251,332],"unnatural,":[190],"unnatural.Noise:":[193],"How":[194,340],"level":[200,232],"scale":[206,240,275,320,352],"describe":[208,242,277,322,354],"its":[209,243,323],"impact:":[210],"5.Not":[211,245],"noIceable,":[212,215],"Slightly":[214,248],"NoIceable":[217],"but":[218],"not":[219],"intrusive,":[220,223],"intrusive.":[226],"Distor1on:How":[227],"distorIon":[234],"quality:":[244],"distorted,":[246,249,252,255],"distorted.":[258],"Listening":[259],"effort:How":[260],"intelligibility":[265],"audio":[268,375],"just":[270],"listened":[271],"to?Use":[272],"your":[278,355],"experience:":[279,356],"Complete":[281],"relaxaIon":[282],"possible;":[283],"no":[284,290],"effort":[285,292,296,300],"required,":[286,293,297,301],"APenIon":[288],"necessary;":[289],"appreciable":[291],"Considerable":[299],"1.No":[302],"meaning":[303],"understood":[304],"with":[305],"any":[306],"feasible":[307],"effort.":[308],"Con1nuity:How":[309],"conInuity":[314],"smoothness:":[324],"smooth,":[327,330,333],"disjointed,":[336],"disjointed.Overall:":[339],"overall":[345],"excellent,":[358],"good,":[360],"fair,":[362],"poor,":[364],"bad.":[366],"Noise":[367],"descrip1on:Please":[368],"analyze":[369],"present":[372],"clip.":[376]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2025-10-10T00:00:00"}
