{"id":"https://openalex.org/W4408345667","doi":"https://doi.org/10.1109/icassp49660.2025.10890590","title":"Enabling Auditory Large Language Models for Automatic Speech Quality Evaluation","display_name":"Enabling Auditory Large Language Models for Automatic Speech Quality Evaluation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345667","doi":"https://doi.org/10.1109/icassp49660.2025.10890590"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890590","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/A5017974335","display_name":"Siyin Wang","orcid":"https://orcid.org/0009-0008-7992-2476"},"institutions":[{"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":true,"raw_author_name":"Siyin Wang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109693003","display_name":"Wenyi Yu","orcid":null},"institutions":[{"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"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016114527","display_name":"Yudong Yang","orcid":"https://orcid.org/0000-0002-7142-2249"},"institutions":[{"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":"Yudong Yang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039664887","display_name":"Changli Tang","orcid":"https://orcid.org/0000-0002-6550-1901"},"institutions":[{"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":"Changli Tang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443484","display_name":"Yixuan Li","orcid":"https://orcid.org/0009-0003-5857-367X"},"institutions":[{"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":"Yixuan Li","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jimin Zhuang","orcid":null},"institutions":[{"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":"Jimin Zhuang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109692700","display_name":"Xianzhao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianzhao Chen","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103156833","display_name":"Xiaohai Tian","orcid":"https://orcid.org/0000-0001-5219-1249"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaohai Tian","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433039","display_name":"Jun Zhang","orcid":"https://orcid.org/0000-0001-5441-3474"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Zhang","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077772423","display_name":"Guangzhi Sun","orcid":"https://orcid.org/0000-0002-5886-056X"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guangzhi Sun","raw_affiliation_strings":["University of Cambridge"],"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107807850","display_name":"Lu L\u00fc","orcid":"https://orcid.org/0000-0002-8290-8834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Lu","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460186","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-5884-2169"},"institutions":[{"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"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5017974335"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":5.1131,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.94681613,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"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/T10860","display_name":"Speech and Audio Processing","score":0.9837999939918518,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9837999939918518,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.900600016117096,"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/computer-science","display_name":"Computer science","score":0.8235548734664917},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5824082493782043},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5666295886039734},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.47576943039894104},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44938910007476807}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8235548734664917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5824082493782043},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5666295886039734},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47576943039894104},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44938910007476807},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890590","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":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1993219564","https://openalex.org/W2972394484","https://openalex.org/W3024869864","https://openalex.org/W3196225973","https://openalex.org/W3196475561","https://openalex.org/W3202278141","https://openalex.org/W3209984917","https://openalex.org/W4225956675","https://openalex.org/W4296068974","https://openalex.org/W4297570641","https://openalex.org/W4372260534","https://openalex.org/W4372263384","https://openalex.org/W4391021666","https://openalex.org/W4392902623","https://openalex.org/W4392902647","https://openalex.org/W4392903872","https://openalex.org/W4392903956","https://openalex.org/W4392931626","https://openalex.org/W4402111259","https://openalex.org/W4402111636","https://openalex.org/W4402112153","https://openalex.org/W4402112249","https://openalex.org/W4402112400","https://openalex.org/W4402684170","https://openalex.org/W4404781855","https://openalex.org/W4406461503","https://openalex.org/W4409362588","https://openalex.org/W4411119642","https://openalex.org/W6729924827","https://openalex.org/W6772383348","https://openalex.org/W6796581206","https://openalex.org/W6847363464","https://openalex.org/W6849177959","https://openalex.org/W6850625674","https://openalex.org/W6853998256","https://openalex.org/W6856800273","https://openalex.org/W6857054612","https://openalex.org/W6859099255","https://openalex.org/W6860041859","https://openalex.org/W6861279438","https://openalex.org/W6861626678","https://openalex.org/W6870775139"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Speech":[0],"quality":[1,52,116],"assessment":[2],"typically":[3],"requires":[4],"evaluating":[5,75],"audio":[6],"from":[7],"multiple":[8],"aspects,":[9],"such":[10,122],"as":[11,123],"mean":[12],"opinion":[13],"score":[14],"(MOS)":[15],"and":[16,66,96,113,126,162,172,180],"speaker":[17],"similarity":[18],"(SIM)":[19],"etc.,":[20],"which":[21,70],"can":[22,184],"be":[23,185],"challenging":[24],"to":[25,62,85,154],"cover":[26],"using":[27,118],"one":[28],"small":[29,157],"model":[30,136,182],"designed":[31],"for":[32,49,74],"a":[33,134],"single":[34],"task.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39],"propose":[40],"leveraging":[41],"recently":[42],"introduced":[43],"auditory":[44,58,81,120,148],"large":[45],"language":[46,88,131,174],"models":[47,158],"(LLMs)":[48],"automatic":[50],"speech":[51,115],"assessment.":[53],"By":[54],"employing":[55],"task-specific":[56,156],"prompts,":[57],"LLMs":[59,121,149],"are":[60,71],"finetuned":[61,80,181],"predict":[63],"MOS,":[64],"SIM":[65],"A/B":[67,170],"testing":[68,171],"results,":[69],"commonly":[72],"used":[73],"text-to-speech":[76],"systems.":[77],"Additionally,":[78],"the":[79,109,129],"LLM":[82],"is":[83,141],"able":[84],"generate":[86],"natural":[87,130,173],"descriptions":[89,132],"assessing":[90],"aspects":[91],"like":[92],"noisiness,":[93],"distortion,":[94],"discontinuity,":[95],"overall":[97],"quality,":[98],"providing":[99],"more":[100],"interpretable":[101],"outputs.":[102],"Extensive":[103],"experiments":[104],"have":[105],"been":[106],"performed":[107],"on":[108],"NISQA,":[110],"BVCC,":[111],"SOMOS":[112],"VoxSim":[114],"datasets,":[117],"open-source":[119],"SALMONN,":[124],"Qwen-Audio,":[125],"Qwen2-Audio.":[127],"For":[128],"task,":[133],"commercial":[135],"Google":[137],"Gemini":[138],"1.5":[139],"Pro":[140],"also":[142,165],"evaluated.":[143],"The":[144],"results":[145,168],"demonstrate":[146],"that":[147],"achieve":[150],"competitive":[151],"performance":[152],"compared":[153],"state-of-the-art":[155],"in":[159,169],"predicting":[160],"MOS":[161],"SIM,":[163],"while":[164],"delivering":[166],"promising":[167],"descriptions.":[175],"Our":[176],"data":[177],"processing":[178],"scripts":[179],"checkpoints":[183],"found":[186],"at":[187],"https://github.com/bytedance/SALMONN.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}