{"id":"https://openalex.org/W4392902637","doi":"https://doi.org/10.1109/icassp48485.2024.10446712","title":"Multi-Task Pseudo-Label Learning for Non-Intrusive Speech Quality Assessment Model","display_name":"Multi-Task Pseudo-Label Learning for Non-Intrusive Speech Quality Assessment Model","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902637","doi":"https://doi.org/10.1109/icassp48485.2024.10446712"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"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":["National Taiwan University","Academia Sinica"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080005842","display_name":"Bo-Ren Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo-Ren Brian Bai","raw_affiliation_strings":["Fortemedia"],"affiliations":[{"raw_affiliation_string":"Fortemedia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027130404","display_name":"Chiou\u2010Shann Fuh","orcid":"https://orcid.org/0000-0002-6174-2556"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chiou-Shann Fuh","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Academia Sinica","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"],"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030281426"],"corresponding_institution_ids":["https://openalex.org/I16733864","https://openalex.org/I84653119"],"apc_list":null,"apc_paid":null,"fwci":0.375,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49357533,"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":"831","last_page":"835"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9988999962806702,"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":0.9983999729156494,"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":0.7741589546203613},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.7432286143302917},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.6250336170196533},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6081239581108093},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5699634552001953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5250627398490906},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4918074905872345},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.457484632730484},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.4392542541027069},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.43667036294937134},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43238940834999084},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41115519404411316},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3100981116294861},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.304020494222641},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.2759711742401123},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.1667734682559967},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08351844549179077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7741589546203613},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.7432286143302917},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.6250336170196533},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6081239581108093},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5699634552001953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5250627398490906},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4918074905872345},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.457484632730484},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.4392542541027069},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.43667036294937134},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43238940834999084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41115519404411316},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3100981116294861},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.304020494222641},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.2759711742401123},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.1667734682559967},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08351844549179077},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2000916836","https://openalex.org/W2046033161","https://openalex.org/W2078483536","https://openalex.org/W2113131123","https://openalex.org/W2121973264","https://openalex.org/W2405774341","https://openalex.org/W2963828919","https://openalex.org/W2964052309","https://openalex.org/W3016129867","https://openalex.org/W3161558238","https://openalex.org/W3202278141","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221144124","https://openalex.org/W4223503417","https://openalex.org/W4225956675","https://openalex.org/W4226198268","https://openalex.org/W4245919820","https://openalex.org/W4296068974","https://openalex.org/W4297841316","https://openalex.org/W4297841451","https://openalex.org/W4311167834"],"related_works":["https://openalex.org/W2144085034","https://openalex.org/W2988616598","https://openalex.org/W3196343857","https://openalex.org/W59212688","https://openalex.org/W2098596704","https://openalex.org/W2295525327","https://openalex.org/W4287113595","https://openalex.org/W3176271478","https://openalex.org/W2189586111","https://openalex.org/W1893647155"],"abstract_inverted_index":{"This":[0],"study":[1],"proposes":[2],"a":[3,24,82,98,134,140],"multi-task":[4],"pseudo-label":[5,21],"learning":[6,73],"(MPL)-based":[7],"non-intrusive":[8],"speech":[9,60,68,177],"quality":[10,61],"assessment":[11,44,178],"model":[12,26,49,135],"called":[13],"MTQ-Net.":[14],"MPL":[15,130,166],"consists":[16],"of":[17,59,129,148,157],"two":[18],"stages:":[19],"obtaining":[20],"scores":[22],"from":[23,86,102,136],"pretrained":[25,47],"and":[27,39,67,93,97,109,138],"performing":[28],"multitask":[29],"learning.":[30],"The":[31,46],"3QUEST":[32],"metrics,":[33],"namely":[34],"Speech-MOS":[35],"(S-MOS),":[36],"Noise-MOS":[37],"(N-MOS),":[38],"General-MOS":[40],"(G-MOS),":[41],"are":[42],"the":[43,87,90,94,103,106,110,114,120,127,146,149,154,162,165],"targets.":[45],"MOSA-Net":[48],"is":[50,74,117,159],"utilized":[51],"to":[52,77,132,174],"estimate":[53],"three":[54],"pseudo":[55,111],"labels:":[56],"perceptual":[57],"evaluation":[58],"(PESQ),":[62],"short-time":[63],"objective":[64],"intelligibility":[65],"(STOI),":[66],"distortion":[69],"index":[70],"(SDI).":[71],"Multi-task":[72],"then":[75],"employed":[76,118],"train":[78],"MTQ-Net":[79,158,163],"by":[80],"combining":[81],"supervised":[83],"loss":[84,100,116,121,151],"(derived":[85,101],"difference":[88,104],"between":[89,105],"estimated":[91,107],"score":[92,108],"ground-truth":[95],"label)":[96],"semi-supervised":[99],"label),":[112],"where":[113],"Huber":[115,150],"as":[119],"function.":[122],"Experimental":[123],"results":[124],"first":[125],"demonstrate":[126],"advantages":[128],"compared":[131,173],"training":[133],"scratch":[137],"using":[139],"direct":[141],"knowledge":[142],"transfer":[143],"mechanism.":[144],"Second,":[145],"benefit":[147],"for":[152],"improving":[153],"predictive":[155,171],"ability":[156],"verified.":[160],"Finally,":[161],"with":[164],"approach":[167],"exhibits":[168],"higher":[169],"overall":[170],"power":[172],"other":[175],"SSL-based":[176],"models.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}