{"id":"https://openalex.org/W4408353637","doi":"https://doi.org/10.1109/icassp49660.2025.10889809","title":"A Study on Zero-shot Non-intrusive Speech Assessment using Large Language Models","display_name":"A Study on Zero-shot Non-intrusive Speech Assessment using Large Language Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353637","doi":"https://doi.org/10.1109/icassp49660.2025.10889809"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889809","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889809","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/A5030281426","display_name":"Ryandhimas E. Zezario","orcid":"https://orcid.org/0000-0001-7319-8263"},"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":true,"raw_author_name":"Ryandhimas E. Zezario","raw_affiliation_strings":["Academia Sinica,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Taipei,Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sabato M. Siniscalchi","raw_affiliation_strings":["University of Palermo,Palermo,Italy"],"affiliations":[{"raw_affiliation_string":"University of Palermo,Palermo,Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"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":"Hsin-Min Wang","raw_affiliation_strings":["Academia Sinica,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Taipei,Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"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,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Taipei,Taiwan","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030281426"],"corresponding_institution_ids":["https://openalex.org/I84653119"],"apc_list":null,"apc_paid":null,"fwci":5.8115,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94981415,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.2953999936580658,"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":0.2953999936580658,"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":0.10909999907016754,"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/T11448","display_name":"Face recognition and analysis","score":0.061000000685453415,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7068862915039062},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6387181878089905},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5039028525352478},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4548746347427368},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33528006076812744},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16911742091178894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7068862915039062},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6387181878089905},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5039028525352478},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4548746347427368},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33528006076812744},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16911742091178894},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889809","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889809","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"},{"id":"pmh:oai:iris.unipa.it:10447/694132","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/694132","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"info:eu-repo/semantics/bookPart"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1582976041","https://openalex.org/W2078483536","https://openalex.org/W2121973264","https://openalex.org/W2963828919","https://openalex.org/W3016129867","https://openalex.org/W3032727804","https://openalex.org/W3161480375","https://openalex.org/W3202278141","https://openalex.org/W3207932315","https://openalex.org/W4221143458","https://openalex.org/W4223503417","https://openalex.org/W4226198268","https://openalex.org/W4245919820","https://openalex.org/W4297841568","https://openalex.org/W4311167834","https://openalex.org/W4372260534","https://openalex.org/W4387363548","https://openalex.org/W4391021560","https://openalex.org/W4392902637","https://openalex.org/W4392903532","https://openalex.org/W4392903985","https://openalex.org/W4392904968","https://openalex.org/W4393178509","https://openalex.org/W4393859250","https://openalex.org/W4402917263","https://openalex.org/W4402981815","https://openalex.org/W4404712190","https://openalex.org/W4408345667","https://openalex.org/W6675521023","https://openalex.org/W6847363464","https://openalex.org/W6861531434"],"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/W3204019825"],"abstract_inverted_index":{"This":[0],"work":[1],"investigates":[2],"two":[3],"strategies":[4],"for":[5,81,136,144],"zero-shot":[6,145],"non-intrusive":[7,127],"speech":[8,70,94,146],"assessment":[9,46,147],"leveraging":[10],"large":[11],"language":[12],"models.":[13],"First,":[14],"we":[15,24],"explore":[16],"the":[17,36,45,63],"audio":[18,82],"analysis":[19],"capabilities":[20],"of":[21,68],"GPT-4o.":[22],"Second,":[23],"propose":[25],"GPT-Whisper,":[26,52],"which":[27],"uses":[28],"Whisper":[29],"as":[30],"an":[31],"audio-to-text":[32],"module":[33],"and":[34,51,59,62,96,98,107,130],"evaluates":[35],"text\u2019s":[37],"naturalness":[38],"via":[39],"targeted":[40],"prompt":[41],"engineering.":[42],"We":[43],"evaluate":[44],"metrics":[47],"predicted":[48],"by":[49],"GPT-4o":[50,76],"examining":[53],"their":[54],"correlation":[55,92,101,135],"with":[56,93,102],"human-based":[57],"quality":[58,95,121],"intelligibility":[60,112],"assessments":[61],"character":[64],"error":[65],"rate":[66],"(CER)":[67],"automatic":[69],"recognition.":[71],"Experimental":[72],"results":[73],"show":[74],"that":[75],"alone":[77],"is":[78],"less":[79],"effective":[80],"analysis,":[83],"while":[84],"GPT-Whisper":[85,109,124],"achieves":[86],"higher":[87,100],"prediction":[88],"accuracy,":[89],"has":[90,99],"moderate":[91],"intelligibility,":[97],"CER.":[103,138],"Compared":[104],"to":[105],"SpeechLMScore":[106,119],"DNSMOS,":[108],"excels":[110],"in":[111,120,132],"metrics,":[113],"but":[114],"performs":[115],"slightly":[116],"worse":[117],"than":[118],"estimation.":[122],"Furthermore,":[123],"outperforms":[125],"supervised":[126],"models":[128],"MOS-SSL":[129],"MTI-Net":[131],"Spearman\u2019s":[133],"rank":[134],"Whisper\u2019s":[137],"These":[139],"findings":[140],"validate":[141],"GPT-Whisper\u2019s":[142],"potential":[143],"without":[148],"requiring":[149],"additional":[150],"training":[151],"data.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-03T08:47:05.690250","created_date":"2025-10-10T00:00:00"}