{"id":"https://openalex.org/W4402981815","doi":"https://doi.org/10.1109/icme57554.2024.10688047","title":"A Study On Incorporating Whisper For Robust Speech Assessment","display_name":"A Study On Incorporating Whisper For Robust Speech Assessment","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402981815","doi":"https://doi.org/10.1109/icme57554.2024.10688047"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Ryandhimas E. Zezario","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/A5100428119","display_name":"Yu\u2010Wen Chen","orcid":"https://orcid.org/0000-0002-4335-7574"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu-Wen Chen","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071471469","display_name":"Szu\u2010Wei Fu","orcid":"https://orcid.org/0000-0002-3487-8212"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Szu-Wei Fu","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"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/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"]}]},{"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/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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5030281426"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":5.5284,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.9672974,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"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":0.7850000262260437,"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":0.7850000262260437,"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":0.7307000160217285,"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/T13191","display_name":"Dispute Resolution and Class Actions","score":0.6481999754905701,"subfield":{"id":"https://openalex.org/subfields/1408","display_name":"Strategy and Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7599682807922363},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3718467354774475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7599682807922363},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3718467354774475}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1976188834","https://openalex.org/W1987831012","https://openalex.org/W2000916836","https://openalex.org/W2047068213","https://openalex.org/W2076824878","https://openalex.org/W2078483536","https://openalex.org/W2121973264","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2405774341","https://openalex.org/W2516001803","https://openalex.org/W2963403924","https://openalex.org/W2963828919","https://openalex.org/W2964052309","https://openalex.org/W2990594533","https://openalex.org/W3015545615","https://openalex.org/W3016129867","https://openalex.org/W3198270377","https://openalex.org/W3199185216","https://openalex.org/W3202278141","https://openalex.org/W3207932315","https://openalex.org/W4221143458","https://openalex.org/W4223503417","https://openalex.org/W4225956675","https://openalex.org/W4226198268","https://openalex.org/W4297841451","https://openalex.org/W4297841568","https://openalex.org/W4311167834","https://openalex.org/W4385807453","https://openalex.org/W4391021432","https://openalex.org/W4391021560","https://openalex.org/W4393859250","https://openalex.org/W6675521023","https://openalex.org/W6785906987","https://openalex.org/W6791808201","https://openalex.org/W6847363464","https://openalex.org/W6858511862"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"This":[0],"research":[1],"introduces":[2],"an":[3],"enhanced":[4],"version":[5],"of":[6,29,132],"the":[7,14,27,67,129,133,140],"multi-objective":[8],"speech":[9,36,89],"assessment":[10,37,90],"model\u2013MOSA-Net+,":[11],"by":[12],"leveraging":[13],"acoustic":[15],"features":[16,57,69],"from":[17,45,70],"Whisper,":[18],"a":[19,33],"large-scaled":[20],"weakly":[21],"supervised":[22],"model.":[23,38],"We":[24],"first":[25],"investigate":[26],"effectiveness":[28],"Whisper":[30,46,71],"in":[31,96,107,128],"deploying":[32],"more":[34,61],"robust":[35],"After":[39],"that,":[40],"we":[41],"explore":[42],"combining":[43,66],"representations":[44],"and":[47,72,86,100],"SSL":[48,73],"models.":[49],"The":[50],"experimental":[51],"results":[52],"reveal":[53],"that":[54],"Whisper\u2019s":[55],"embedding":[56,68],"can":[58],"contribute":[59],"to":[60,77,82],"accurate":[62],"prediction":[63],"performance.":[64],"Moreover,":[65],"models":[74],"only":[75],"leads":[76],"marginal":[78],"improvement.":[79],"As":[80],"compared":[81],"intrusive":[83],"methods,":[84],"MOSA-Net,":[85],"other":[87],"SSL-based":[88],"models,":[91],"MOSA-Net+":[92,125],"yields":[93],"notable":[94],"improvements":[95],"estimating":[97],"subjective":[98],"quality":[99],"intelligibility":[101],"scores":[102],"across":[103],"all":[104],"evaluation":[105],"metrics":[106],"Taiwan":[108],"Mandarin":[109],"Hearing":[110],"In":[111],"Noise":[112],"test":[113],"-":[114],"Quality":[115],"&":[116],"Intelligibility":[117],"(TMHINT-QI)":[118],"dataset.":[119],"To":[120],"further":[121],"validate":[122],"its":[123],"robustness,":[124],"was":[126],"tested":[127],"noisy-and-enhanced":[130],"track":[131],"VoiceMOS":[134],"Challenge":[135],"2023,":[136],"where":[137],"it":[138],"obtained":[139],"top-ranked":[141],"performance":[142],"among":[143],"nine":[144],"systems.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
