{"id":"https://openalex.org/W4372266987","doi":"https://doi.org/10.1109/icassp49357.2023.10094635","title":"Explanations for Automatic Speech Recognition","display_name":"Explanations for Automatic Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266987","doi":"https://doi.org/10.1109/icassp49357.2023.10094635"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/f220cfa8-6680-4fd1-afc5-22ecaf7dd721","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041239475","display_name":"Xiaoliang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Xiaoliang Wu","raw_affiliation_strings":["University of Edinburgh,School of Informatics","School of Informatics, University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,School of Informatics","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics, University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["University of Edinburgh,School of Informatics","School of Informatics, University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,School of Informatics","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics, University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079075574","display_name":"Ajitha Rajan","orcid":"https://orcid.org/0000-0003-3765-3075"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ajitha Rajan","raw_affiliation_strings":["University of Edinburgh,School of Informatics","School of Informatics, University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,School of Informatics","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics, University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041239475"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.8987,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7835556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9995999932289124,"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":0.9995999932289124,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9886000156402588,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.965399980545044,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8345013856887817},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7681164741516113},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5827741622924805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5578224658966064},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5236178040504456},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4909391701221466},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4899234175682068},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4092588424682617},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3664684295654297}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8345013856887817},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7681164741516113},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5827741622924805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5578224658966064},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5236178040504456},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4909391701221466},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4899234175682068},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4092588424682617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3664684295654297},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/f220cfa8-6680-4fd1-afc5-22ecaf7dd721","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f220cfa8-6680-4fd1-afc5-22ecaf7dd721","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wu, X, Bell, P & Rajan, A 2023, Explanations for automatic speech recognition. in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Institute of Electrical and Electronics Engineers, 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes Island, Greece, 4/06/23. https://doi.org/10.1109/ICASSP49357.2023.10094635","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/f220cfa8-6680-4fd1-afc5-22ecaf7dd721","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f220cfa8-6680-4fd1-afc5-22ecaf7dd721","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wu, X, Bell, P & Rajan, A 2023, Explanations for automatic speech recognition. in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Institute of Electrical and Electronics Engineers, 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes Island, Greece, 4/06/23. https://doi.org/10.1109/ICASSP49357.2023.10094635","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6399999856948853,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1922655562","https://openalex.org/W2123807288","https://openalex.org/W2282821441","https://openalex.org/W2594633041","https://openalex.org/W2605409611","https://openalex.org/W2807124908","https://openalex.org/W2912083425","https://openalex.org/W2964710935","https://openalex.org/W2970641574","https://openalex.org/W3015870704","https://openalex.org/W3023478397","https://openalex.org/W3134073633","https://openalex.org/W3187467055","https://openalex.org/W4243127898","https://openalex.org/W4243590587","https://openalex.org/W4288313203","https://openalex.org/W4300855260","https://openalex.org/W4376561633","https://openalex.org/W6640090968","https://openalex.org/W6640608520","https://openalex.org/W6734194636","https://openalex.org/W6736518430","https://openalex.org/W6737947904","https://openalex.org/W6765558359","https://openalex.org/W6766154603","https://openalex.org/W6771467084","https://openalex.org/W6776908535","https://openalex.org/W6791235587"],"related_works":["https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W4241418540","https://openalex.org/W2018477250","https://openalex.org/W3119814709","https://openalex.org/W1508895727","https://openalex.org/W2725786787","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"We":[0,128],"address":[1],"quality":[2,131],"assessment":[3],"for":[4,63,120],"neural":[5],"network":[6],"based":[7],"ASR":[8,65,121,143],"by":[9,54,136],"providing":[10],"explanations":[11,134],"that":[12,73],"help":[13,22],"increase":[14],"our":[15,126],"understanding":[16],"of":[17,70,81,113,132,151],"the":[18,26,82,130,133,137,148,162],"system":[19],"and":[20,45,78,103,157],"ultimately":[21],"build":[23],"trust":[24],"in":[25,125],"system.":[27],"Compared":[28],"to":[29],"simple":[30],"classification":[31,96],"labels,":[32],"explaining":[33],"transcriptions":[34,46],"is":[35,42,51,74],"more":[36],"challenging":[37],"as":[38,47,67,122],"judging":[39],"their":[40],"correctness":[41],"not":[43,52],"straightforward":[44],"a":[48,68,76,123],"variable-length":[49],"sequence":[50],"handled":[53],"existing":[55,89],"interpretable":[56],"machine":[57],"learning":[58],"models.We":[59],"provide":[60],"an":[61,64,110],"explanation":[62],"transcription":[66],"subset":[69],"audio":[71,159],"frames":[72],"both":[75],"minimal":[77],"sufficient":[79],"cause":[80],"transcription.":[83],"To":[84],"do":[85],"this,":[86],"we":[87,108],"adapt":[88],"explainable":[90],"AI":[91],"(XAI)":[92],"techniques":[93,139],"from":[94,161],"image":[95],"-":[97],"(1)":[98],"Statistical":[99],"Fault":[100],"Localisation(SFL)":[101],"[1]":[102],"(2)":[104],"Causal":[105],"[2].":[106],"Additionally,":[107],"use":[109],"adapted":[111],"version":[112],"Local":[114],"Interpretable":[115],"Model-Agnostic":[116],"Explanations":[117],"(LIME)":[118],"[3]":[119],"baseline":[124,149],"experiments.":[127],"evaluate":[129],"generated":[135],"proposed":[138],"over":[140],"three":[141],"different":[142],"\u2013":[144,156],"Google":[145],"API":[146],"[4],":[147],"model":[150],"Sphinx":[152],"[5],":[153],"Deepspeech":[154],"[6]":[155],"100":[158],"samples":[160],"Commonvoice":[163],"dataset":[164],"[7].":[165]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}