{"id":"https://openalex.org/W4406859936","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848735","title":"A Non-Intrusive Speech Quality Assessment Model using Whisper and Multi-Head Attention","display_name":"A Non-Intrusive Speech Quality Assessment Model using Whisper and Multi-Head Attention","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406859936","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848735"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5085047691","display_name":"Gary Lin","orcid":"https://orcid.org/0000-0002-2269-1135"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guojian Lin","raw_affiliation_strings":["Southern University of Science and Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation,Academia Sinica,Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation,Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100405410","display_name":"Fei Chen","orcid":"https://orcid.org/0000-0002-6988-492X"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Chen","raw_affiliation_strings":["Southern University of Science and Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085047691"],"corresponding_institution_ids":["https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":0.3455,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6080988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8894000053405762,"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":0.8894000053405762,"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/computer-science","display_name":"Computer science","score":0.7658983469009399},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5988429188728333},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5642609596252441},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5087054371833801},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3222328722476959},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.05237731337547302}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7658983469009399},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5988429188728333},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5642609596252441},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5087054371833801},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3222328722476959},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.05237731337547302},{"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},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10848735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2127851351","https://openalex.org/W2963403924","https://openalex.org/W2964052309","https://openalex.org/W2972394484","https://openalex.org/W3015545615","https://openalex.org/W3032727804","https://openalex.org/W3161558238","https://openalex.org/W3202278141","https://openalex.org/W3207932315","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4223503417","https://openalex.org/W4225956675","https://openalex.org/W4226198268","https://openalex.org/W4296068974","https://openalex.org/W4296070386","https://openalex.org/W4311167834","https://openalex.org/W4391021560","https://openalex.org/W4391021629","https://openalex.org/W4393185179","https://openalex.org/W4402981815","https://openalex.org/W6675521023","https://openalex.org/W6785906987","https://openalex.org/W6847363464","https://openalex.org/W6848208918","https://openalex.org/W6855898989"],"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":[1,27,79,146,160],"assessment":[2,147],"serves":[3],"as":[4],"an":[5],"important":[6],"tool":[7],"for":[8],"speech":[9,78,145],"related":[10],"applications.":[11],"In":[12],"this":[13],"study,":[14],"we":[15],"propose":[16],"a":[17,39,53,173],"non-intrusive":[18],"model":[19,41,104,186],"QUAL-Net,":[20],"which":[21],"is":[22,155],"able":[23],"to":[24,64,115,157,178,182],"estimate":[25,158],"subjective":[26,159],"scores":[28],"of":[29,97,136,184],"the":[30,90,107,131,164,179,185],"target":[31],"speech.":[32],"QUAL-Net":[33,51,149,162,171],"combines":[34],"acoustic":[35,98,121],"features":[36,45,74,99,122],"extracted":[37],"by":[38],"large-scale":[40],"Whisper":[42,72],"with":[43,141],"spectral":[44],"and":[46,56,133,143],"time-domain":[47],"waveform":[48],"features.":[49,88],"Furthermore,":[50,106],"employs":[52],"CNN-BiLSTM-Attention":[54],"architecture":[55,176],"introduces":[57],"multi-head":[58,111],"attention":[59,62,112],"mechanism":[60],"into":[61],"layer":[63],"enhance":[65],"model\u2019s":[66],"performance.":[67,105],"Experimental":[68],"results":[69,108],"demonstrate":[70],"that":[71,110],"embedding":[73,87],"have":[75],"more":[76,117],"powerful":[77],"characterization":[80],"ability":[81],"than":[82,123],"other":[83,144],"self-supervised":[84],"learning":[85],"(SSL)":[86],"Additionally,":[89],"feature":[91],"combination":[92],"utilizing":[93],"all":[94,168],"three":[95],"types":[96],"obtains":[100],"optimal":[101],"improvement":[102,152],"in":[103,167],"prove":[109],"has":[113],"potential":[114],"capture":[116],"key":[118],"information":[119],"from":[120],"multiplicative":[124],"self-attention.":[125],"We":[126],"tested":[127],"QUAL-Net\u2019s":[128],"performance":[129],"on":[130],"noisy":[132],"enhanced":[134],"track":[135],"VoiceMOS":[137],"Challenge":[138],"2023.":[139],"Compared":[140],"MOSA-Net":[142],"models,":[148],"achieves":[150],"significant":[151],"when":[153],"it":[154],"trained":[156],"scores.":[161],"outperforms":[163],"top-ranked":[165],"MOSA-Net+":[166],"evaluation":[169],"metrics.":[170],"uses":[172],"simpler":[174],"CNN":[175],"compared":[177],"MOSA-Net+,":[180],"contributing":[181],"reduction":[183],"complexity.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}