{"id":"https://openalex.org/W4297841568","doi":"https://doi.org/10.21437/interspeech.2022-10828","title":"MTI-Net: A Multi-Target Speech Intelligibility Prediction Model","display_name":"MTI-Net: A Multi-Target Speech Intelligibility Prediction Model","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841568","doi":"https://doi.org/10.21437/interspeech.2022-10828"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10828","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10828","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ryandhimas Edo Zezario","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071471469","display_name":"Szu\u2010Wei Fu","orcid":"https://orcid.org/0000-0002-3487-8212"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Szu-wei Fu","raw_affiliation_strings":["Microsoft Corporation,"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","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 of China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology of China","institution_ids":["https://openalex.org/I3045169105"]}]},{"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":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5030281426"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.216,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81706549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5463","last_page":"5467"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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":0.6958305835723877},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6375486254692078},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6044554710388184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33218222856521606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6958305835723877},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6375486254692078},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6044554710388184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33218222856521606},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10828","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10828","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1582976041","https://openalex.org/W1985029311","https://openalex.org/W1987831012","https://openalex.org/W2000916836","https://openalex.org/W2086906794","https://openalex.org/W2092644348","https://openalex.org/W2121973264","https://openalex.org/W2125114513","https://openalex.org/W2141998673","https://openalex.org/W2405774341","https://openalex.org/W2809874909","https://openalex.org/W2963828919","https://openalex.org/W3015545615","https://openalex.org/W3016070314","https://openalex.org/W3016129867","https://openalex.org/W3049256661","https://openalex.org/W3105857760","https://openalex.org/W3107873282","https://openalex.org/W3129991388","https://openalex.org/W3169320628","https://openalex.org/W3189296823","https://openalex.org/W3197259906","https://openalex.org/W3197580070","https://openalex.org/W3202278141","https://openalex.org/W3209126739","https://openalex.org/W3209984917","https://openalex.org/W3211224152","https://openalex.org/W4224933800","https://openalex.org/W4226029459","https://openalex.org/W4299959846","https://openalex.org/W4311137818","https://openalex.org/W4311167834"],"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/W2127461790","https://openalex.org/W2069324367"],"abstract_inverted_index":{"Recently,":[0],"deep":[1,41],"learning":[2,42,109,123,126],"(DL)-based":[3],"non-intrusive":[4],"speech":[5,52,68],"assessment":[6,20],"models":[7,17,43],"have":[8],"attracted":[9],"great":[10],"attention.Many":[11],"studies":[12,39],"report":[13],"that":[14,90,156],"these":[15],"DL-based":[16],"yield":[18],"satisfactory":[19],"performance":[21,27,95],"and":[22,62,80,105,112,124,149,159],"good":[23],"flexibility,":[24],"but":[25],"their":[26],"in":[28],"unseen":[29],"environments":[30],"remains":[31],"a":[32,50,67],"challenge.Furthermore,":[33],"compared":[34],"to":[35,44,73],"quality":[36],"scores,":[37],"fewer":[38],"elaborate":[40],"estimate":[45],"intelligibility":[46,53,64,158],"scores.This":[47],"study":[48],"proposes":[49],"multi-task":[51,147],"prediction":[54,94,113],"model,":[55],"called":[56],"MTI-Net,":[57],"for":[58],"simultaneously":[59],"predicting":[60],"human":[61,75],"machine":[63],"measures.Specifically,":[65],"given":[66],"utterance,":[69],"MTI-Net":[70,164],"is":[71,154],"designed":[72],"predict":[74],"subjective":[76],"listening":[77],"test":[78],"results":[79,139],"word":[81],"error":[82],"rate":[83],"(WER)":[84],"scores.We":[85],"also":[86],"investigate":[87],"several":[88],"methods":[89],"can":[91],"improve":[92],"the":[93,119,132,141,157,169],"of":[96,115,121,135,143],"MTI-Net.First,":[97],"we":[98,117,130],"compare":[99],"different":[100],"features":[101,104],"(including":[102],"low-level":[103],"embeddings":[106],"from":[107],"self-supervised":[108],"(SSL)":[110],"models)":[111],"targets":[114],"MTI-Net.Second,":[116],"explore":[118],"effect":[120],"transfer":[122],"multi-tasking":[125],"on":[127],"training":[128],"MTI-Net.Finally,":[129],"examine":[131],"potential":[133],"advantages":[134],"fine-tuning":[136,150],"SSL":[137,151],"embeddings.Experimental":[138],"demonstrate":[140],"effectiveness":[142],"using":[144],"cross-domain":[145],"features,":[146],"learning,":[148],"embeddings.Furthermore,":[152],"it":[153],"confirmed":[155],"WER":[160],"scores":[161],"predicted":[162],"by":[163],"are":[165],"highly":[166],"correlated":[167],"with":[168],"ground-truth":[170],"scores.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}