{"id":"https://openalex.org/W4226198268","doi":"https://doi.org/10.21437/interspeech.2022-10153","title":"InQSS: a speech intelligibility and quality assessment model using a multi-task learning network","display_name":"InQSS: a speech intelligibility and quality assessment model using a multi-task learning network","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4226198268","doi":"https://doi.org/10.21437/interspeech.2022-10153"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10153","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10153","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/A5100428120","display_name":"Yu-Wen Chen","orcid":"https://orcid.org/0000-0002-7084-7632"},"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":true,"raw_author_name":"Yu-Wen Chen","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/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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100428120"],"corresponding_institution_ids":["https://openalex.org/I4210086894"],"apc_list":null,"apc_paid":null,"fwci":1.5591,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.84766214,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"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/T10860","display_name":"Speech and Audio Processing","score":0.9922999739646912,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9681000113487244,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7973402142524719},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7678102254867554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5692627429962158},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48350051045417786},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45745575428009033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3746262490749359},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08341702818870544}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973402142524719},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7678102254867554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5692627429962158},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48350051045417786},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45745575428009033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3746262490749359},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08341702818870544},{"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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10153","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10153","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":0.6700000166893005,"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":37,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1728888090","https://openalex.org/W1994906459","https://openalex.org/W2000916836","https://openalex.org/W2082668798","https://openalex.org/W2093231248","https://openalex.org/W2108708552","https://openalex.org/W2121973264","https://openalex.org/W2141998673","https://openalex.org/W2159202424","https://openalex.org/W2400549570","https://openalex.org/W2405774341","https://openalex.org/W2485763638","https://openalex.org/W2765278963","https://openalex.org/W2809874909","https://openalex.org/W2908414239","https://openalex.org/W2933138175","https://openalex.org/W2940385941","https://openalex.org/W2963403924","https://openalex.org/W2963828919","https://openalex.org/W2972394484","https://openalex.org/W2972777526","https://openalex.org/W2973133192","https://openalex.org/W3016129867","https://openalex.org/W3096643087","https://openalex.org/W3096690837","https://openalex.org/W3097627357","https://openalex.org/W3097906045","https://openalex.org/W3103840368","https://openalex.org/W3120557855","https://openalex.org/W3147454823","https://openalex.org/W3161558238","https://openalex.org/W3196475561","https://openalex.org/W3198270377","https://openalex.org/W3200245256","https://openalex.org/W3202278141","https://openalex.org/W4311137818"],"related_works":["https://openalex.org/W2611614995","https://openalex.org/W2368651715","https://openalex.org/W2789919619","https://openalex.org/W1552159754","https://openalex.org/W2148757832","https://openalex.org/W4321496520","https://openalex.org/W2293457016","https://openalex.org/W3107474891","https://openalex.org/W2081647779","https://openalex.org/W3185852197"],"abstract_inverted_index":{"Speech":[0],"intelligibility":[1,27,53,70,103],"and":[2,13,28,52,58,71,81],"quality":[3,29,51,72,108],"assessment":[4,30],"models":[5,25],"are":[6],"essential":[7],"tools":[8],"for":[9,26,69],"researchers":[10],"to":[11,32],"evaluate":[12],"improve":[14],"speech":[15,46,112],"processing":[16],"models.However,":[17],"only":[18,101],"a":[19,64,111],"few":[20],"studies":[21],"have":[22],"investigated":[23],"multi-task":[24,66],"due":[31],"the":[33,43,50,75,79,82,88,91,95,102,107],"limitations":[34],"of":[35,55,90,110],"available":[36],"data.In":[37],"this":[38],"study,":[39],"we":[40,61],"released":[41],"TMHINT-QI,":[42],"first":[44],"Chinese":[45],"dataset":[47],"that":[48],"records":[49],"scores":[54,104,109],"clean,":[56],"noisy,":[57],"enhanced":[59],"utterances.Then,":[60],"propose":[62],"InQSS,":[63],"non-intrusive":[65],"learning":[67],"framework":[68],"assessment.We":[73],"evaluated":[74],"InQSS":[76,92],"on":[77],"both":[78],"training-from-scratch":[80],"pretrained":[83],"models.The":[84],"experimental":[85],"results":[86],"confirm":[87],"effectiveness":[89],"framework.In":[93],"addition,":[94],"resulting":[96],"model":[97],"can":[98],"predict":[99],"not":[100],"but":[105],"also":[106],"signal.":[113]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}