{"id":"https://openalex.org/W7155544683","doi":"https://doi.org/10.1109/icsc67292.2026.00053","title":"Explainability in Speech AI: Challenges and Future Directions","display_name":"Explainability in Speech AI: Challenges and Future Directions","publication_year":2026,"publication_date":"2026-02-02","ids":{"openalex":"https://openalex.org/W7155544683","doi":"https://doi.org/10.1109/icsc67292.2026.00053"},"language":null,"primary_location":{"id":"doi:10.1109/icsc67292.2026.00053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsc67292.2026.00053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Semantic Computing (ICSC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5134473964","display_name":"Xiaoliang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaoliang Wu","raw_affiliation_strings":["University of Southampton,Electronics and Computer Science,Southampton,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southampton,Electronics and Computer Science,Southampton,United Kingdom","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134513515","display_name":"Sarah Kiden","orcid":null},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sarah Kiden","raw_affiliation_strings":["University of Southampton,Electronics and Computer Science,Southampton,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southampton,Electronics and Computer Science,Southampton,United Kingdom","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134529509","display_name":"Rui Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Chu","raw_affiliation_strings":["Tufts University,Electrical and Computer Engineering,Medford,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University,Electrical and Computer Engineering,Medford,MA,USA","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009177807","display_name":"Jim Williams","orcid":"https://orcid.org/0000-0002-1464-2317"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jennifer Williams","raw_affiliation_strings":["University of Southampton,Electronics and Computer Science,Southampton,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southampton,Electronics and Computer Science,Southampton,United Kingdom","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134512315","display_name":"Shuo Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuo Zhang","raw_affiliation_strings":["Tufts University,Data Analytics,Medford,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University,Data Analytics,Medford,MA,USA","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134491873","display_name":"Alice Mello Da Fonseca","orcid":null},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alice Mello Da Fonseca","raw_affiliation_strings":["Tufts University,Data Analytics,Medford,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University,Data Analytics,Medford,MA,USA","institution_ids":["https://openalex.org/I121934306"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"320","last_page":"327"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8863999843597412,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8863999843597412,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.009600000455975533,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.006200000178068876,"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/focus","display_name":"Focus (optics)","score":0.29190000891685486},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2727999985218048},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.22220000624656677},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.22210000455379486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4652000069618225},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2770000100135803},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.23899999260902405},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23100000619888306},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.22920000553131104},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.22220000624656677},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.22210000455379486},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.22139999270439148}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsc67292.2026.00053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsc67292.2026.00053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Semantic Computing (ICSC)","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":43,"referenced_works":["https://openalex.org/W1787224781","https://openalex.org/W1849277567","https://openalex.org/W1985198345","https://openalex.org/W2057563799","https://openalex.org/W2072206615","https://openalex.org/W2085662862","https://openalex.org/W2090042521","https://openalex.org/W2127141656","https://openalex.org/W2145812971","https://openalex.org/W2150769028","https://openalex.org/W2154278880","https://openalex.org/W2160815625","https://openalex.org/W2327501763","https://openalex.org/W2516809705","https://openalex.org/W2657631929","https://openalex.org/W2766219058","https://openalex.org/W2794506738","https://openalex.org/W2915253508","https://openalex.org/W2962689740","https://openalex.org/W2962858109","https://openalex.org/W2963134917","https://openalex.org/W2963240019","https://openalex.org/W2963749936","https://openalex.org/W2970726176","https://openalex.org/W3024869864","https://openalex.org/W3041694242","https://openalex.org/W3097777922","https://openalex.org/W3117696238","https://openalex.org/W3156027765","https://openalex.org/W3160584619","https://openalex.org/W4223587462","https://openalex.org/W4237182219","https://openalex.org/W4245744384","https://openalex.org/W4245838404","https://openalex.org/W4294975502","https://openalex.org/W4307359761","https://openalex.org/W4372266987","https://openalex.org/W4389619460","https://openalex.org/W4389917623","https://openalex.org/W4391745456","https://openalex.org/W4392904235","https://openalex.org/W4408119538","https://openalex.org/W4415433804"],"related_works":[],"abstract_inverted_index":{"As":[0],"speech":[1,38,59,65,78,96,100,120],"AI":[2],"models":[3],"are":[4,45],"increasingly":[5],"deployed":[6],"at":[7],"scale":[8],"across":[9,94],"a":[10,27,70,81],"wide":[11],"range":[12],"of":[13,30,42,58,64,73,119],"applications,":[14],"understanding":[15],"their":[16],"decision":[17,114],"behaviour":[18],"has":[19,32],"become":[20],"an":[21],"important":[22],"research":[23],"concern.":[24],"In":[25],"response,":[26],"growing":[28],"body":[29],"work":[31],"applied":[33],"post-hoc":[34,74],"explainability":[35,75],"techniques":[36],"to":[37],"models.":[39],"However,":[40],"many":[41],"these":[43,91],"methods":[44,76,92],"adapted":[46],"from":[47,112],"other":[48],"modalities":[49],"and":[50,85,104,107,116,134],"do":[51],"not":[52],"fully":[53],"account":[54],"for":[55,77,130],"the":[56,62,117],"structure":[57],"signals":[60],"or":[61],"diversity":[63],"tasks.":[66],"This":[67],"paper":[68],"provides":[69],"structured":[71],"overview":[72],"AI,":[79],"with":[80],"focus":[82],"on":[83,123],"perturbation-based":[84],"gradient-based":[86],"approaches.":[87],"We":[88],"analyse":[89],"how":[90],"behave":[93],"representative":[95],"tasks,":[97],"including":[98],"automatic":[99],"recognition,":[101],"speaker":[102],"verification,":[103],"paralinguistic":[105],"analysis,":[106,125],"highlight":[108],"challenges":[109],"that":[110],"arise":[111],"task-specific":[113],"mechanisms":[115],"nature":[118],"signals.":[121],"Based":[122],"this":[124],"we":[126],"outline":[127],"key":[128],"directions":[129],"developing":[131],"more":[132],"task-aware":[133],"speech-specific":[135],"explanation":[136],"frameworks.":[137]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-25T00:00:00"}