{"id":"https://openalex.org/W3015545615","doi":"https://doi.org/10.1109/icassp40776.2020.9053366","title":"An Attention Enhanced Multi-Task Model for Objective Speech Assessment in Real-World Environments","display_name":"An Attention Enhanced Multi-Task Model for Objective Speech Assessment in Real-World Environments","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015545615","doi":"https://doi.org/10.1109/icassp40776.2020.9053366","mag":"3015545615"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5002427662","display_name":"Xuan Dong","orcid":"https://orcid.org/0000-0003-0630-0701"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xuan Dong","raw_affiliation_strings":["Department of Computer Science, Indiana University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Indiana University, USA","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054209447","display_name":"Donald S. Williamson","orcid":"https://orcid.org/0000-0002-7997-5403"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donald S. Williamson","raw_affiliation_strings":["Department of Computer Science, Indiana University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Indiana University, USA","institution_ids":["https://openalex.org/I592451"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002427662"],"corresponding_institution_ids":["https://openalex.org/I592451"],"apc_list":null,"apc_paid":null,"fwci":4.8491,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.96069783,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"911","last_page":"915"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9986000061035156,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8056199550628662},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.677386462688446},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6328916549682617},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6012325882911682},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5989624857902527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5165182948112488},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4360504448413849},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42818647623062134},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4225269854068756},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3463061451911926}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8056199550628662},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.677386462688446},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6328916549682617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6012325882911682},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5989624857902527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5165182948112488},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4360504448413849},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42818647623062134},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4225269854068756},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3463061451911926},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1582976041","https://openalex.org/W1902237438","https://openalex.org/W1975163393","https://openalex.org/W2025401819","https://openalex.org/W2039846947","https://openalex.org/W2094035326","https://openalex.org/W2105854852","https://openalex.org/W2117678320","https://openalex.org/W2125114513","https://openalex.org/W2127851351","https://openalex.org/W2133564696","https://openalex.org/W2141998673","https://openalex.org/W2142690424","https://openalex.org/W2143175575","https://openalex.org/W2153038597","https://openalex.org/W2342810974","https://openalex.org/W2516001803","https://openalex.org/W2516342150","https://openalex.org/W2557915412","https://openalex.org/W2602577565","https://openalex.org/W2624871570","https://openalex.org/W2785712565","https://openalex.org/W2796485741","https://openalex.org/W2809874909","https://openalex.org/W2889128201","https://openalex.org/W2889830381","https://openalex.org/W2913340405","https://openalex.org/W2922332774","https://openalex.org/W2938881288","https://openalex.org/W2939156090","https://openalex.org/W2963040451","https://openalex.org/W2963403868","https://openalex.org/W2963403924","https://openalex.org/W2963954250","https://openalex.org/W2964308564","https://openalex.org/W2990118552","https://openalex.org/W4385245566","https://openalex.org/W6656670161","https://openalex.org/W6676063915","https://openalex.org/W6679434410","https://openalex.org/W6680862256","https://openalex.org/W6681300242","https://openalex.org/W6729924827","https://openalex.org/W6739365718","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W2174706483","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W2997121352","https://openalex.org/W419536403"],"abstract_inverted_index":{"Computational":[0],"objective":[1,89,168],"metrics":[2],"that":[3,108],"use":[4],"reference":[5],"signals":[6],"have":[7,30,57],"been":[8,31,59],"shown":[9],"to":[10,39,120,141],"be":[11],"effective":[12,34],"forms":[13,35],"of":[14,36,52,87],"speech":[15,79],"assessment":[16,38,42,53,80],"in":[17,61,94,110,152],"simulated":[18,95,153],"environments,":[19,157],"since":[20],"they":[21,56],"are":[22,161],"correlated":[23,163],"with":[24,164],"subjective":[25],"listening":[26],"studies.":[27],"Recent":[28],"efforts":[29],"dedicated":[32],"towards":[33],"reference-less":[37,71],"make":[40],"real-world":[41,62,97,155],"more":[43],"practical,":[44],"but":[45],"these":[46],"approaches":[47],"predict":[48],"a":[49,69],"limited":[50],"number":[51],"measures":[54,93],"and":[55,91,96,128,154],"not":[58],"evaluated":[60],"conditions.":[63],"In":[64],"this":[65],"work,":[66],"we":[67],"present":[68],"novel":[70],"based":[72],"framework":[73],"called":[74],"the":[75,125,132,149,159,165],"attention":[76,116],"enhanced":[77],"multi-task":[78,100],"(AMSA)":[81],"model,":[82],"which":[83],"provides":[84],"reliable":[85],"estimates":[86],"multiple":[88],"quality":[90],"intelligibility":[92],"environments.":[98],"The":[99],"learning":[101],"(MTL)":[102],"architecture":[103],"effectively":[104],"generates":[105],"discriminative":[106],"features":[107,123],"assist":[109],"improving":[111],"our":[112],"model's":[113],"robustness.":[114],"An":[115],"mechanism":[117],"is":[118,138],"employed":[119],"identify":[121],"key":[122],"within":[124],"feature":[126],"space,":[127],"it":[129],"noticeably":[130],"reduces":[131],"estimation":[133],"errors.":[134],"A":[135],"classification-aided":[136],"module":[137],"also":[139],"included":[140],"further":[142],"suppress":[143],"prediction":[144],"outliers.":[145],"Our":[146],"model":[147],"achieves":[148],"state-of-the-art":[150],"performance":[151],"data":[156],"where":[158],"results":[160],"strongly":[162],"corresponding":[166],"reference-based":[167],"scores.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}