{"id":"https://openalex.org/W2914479667","doi":"https://doi.org/10.18653/v1/w18-5421","title":"Introspection for convolutional automatic speech recognition","display_name":"Introspection for convolutional automatic speech recognition","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2914479667","doi":"https://doi.org/10.18653/v1/w18-5421","mag":"2914479667"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-5421","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5421","pdf_url":"https://www.aclweb.org/anthology/W18-5421.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-5421.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103238556","display_name":"Andreas Krug","orcid":null},"institutions":[{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Andreas Krug","raw_affiliation_strings":["University of Potsdam, Research Focus Cognitive Sciences Karl-Liebknecht-Str. 24/25, 14476 Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"University of Potsdam, Research Focus Cognitive Sciences Karl-Liebknecht-Str. 24/25, 14476 Potsdam, Germany","institution_ids":["https://openalex.org/I176453806"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034558147","display_name":"Sebastian Stober","orcid":"https://orcid.org/0000-0002-1717-4133"},"institutions":[{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Stober","raw_affiliation_strings":["University of Potsdam, Research Focus Cognitive Sciences Karl-Liebknecht-Str. 24/25, 14476 Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"University of Potsdam, Research Focus Cognitive Sciences Karl-Liebknecht-Str. 24/25, 14476 Potsdam, Germany","institution_ids":["https://openalex.org/I176453806"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103238556"],"corresponding_institution_ids":["https://openalex.org/I176453806"],"apc_list":null,"apc_paid":null,"fwci":1.6924,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88589033,"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":"187","last_page":"199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9976999759674072,"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/T10320","display_name":"Neural Networks and Applications","score":0.9976999759674072,"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":0.9944000244140625,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9879999756813049,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8914487957954407},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8341102600097656},{"id":"https://openalex.org/keywords/introspection","display_name":"Introspection","score":0.8006640076637268},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7408763766288757},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7251140475273132},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6683327555656433},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5146949887275696},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4889017641544342},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4454598128795624},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4425271153450012},{"id":"https://openalex.org/keywords/observer","display_name":"Observer (physics)","score":0.43085813522338867},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42026498913764954},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4147006869316101}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8914487957954407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8341102600097656},{"id":"https://openalex.org/C129671850","wikidata":"https://www.wikidata.org/wiki/Q210501","display_name":"Introspection","level":2,"score":0.8006640076637268},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7408763766288757},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7251140475273132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6683327555656433},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5146949887275696},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4889017641544342},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4454598128795624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4425271153450012},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.43085813522338867},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42026498913764954},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4147006869316101},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w18-5421","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5421","pdf_url":"https://www.aclweb.org/anthology/W18-5421.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-5421","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5421","pdf_url":"https://www.aclweb.org/anthology/W18-5421.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G352791218","display_name":null,"funder_award_id":"(BMBF)","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G6955755495","display_name":null,"funder_award_id":"Germany","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2914479667.pdf","grobid_xml":"https://content.openalex.org/works/W2914479667.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1787224781","https://openalex.org/W1825675169","https://openalex.org/W1849277567","https://openalex.org/W1915485278","https://openalex.org/W1923697677","https://openalex.org/W1932198206","https://openalex.org/W1995562189","https://openalex.org/W2083844448","https://openalex.org/W2097117768","https://openalex.org/W2123045220","https://openalex.org/W2163605009","https://openalex.org/W2172097686","https://openalex.org/W2195388612","https://openalex.org/W2295676751","https://openalex.org/W2399733683","https://openalex.org/W2511774920","https://openalex.org/W2520160253","https://openalex.org/W2525778437","https://openalex.org/W2742004888","https://openalex.org/W2765860599","https://openalex.org/W2898422183","https://openalex.org/W2962858109","https://openalex.org/W2963303951","https://openalex.org/W2963382180","https://openalex.org/W2963464195","https://openalex.org/W2964121744","https://openalex.org/W4297752781"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W4387404794","https://openalex.org/W2380479582","https://openalex.org/W2888392564","https://openalex.org/W4387405288","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4387404506","https://openalex.org/W4390569940","https://openalex.org/W4361193272"],"abstract_inverted_index":{"Artificial":[0],"Neural":[1,149],"Networks":[2,150],"(ANNs)":[3],"have":[4,30],"experienced":[5],"great":[6],"success":[7],"in":[8,43,105],"the":[9,56,70],"past":[10],"few":[11],"years.":[12],"The":[13],"increasing":[14],"complexity":[15],"of":[16,72,119,132,160],"these":[17,113],"models":[18],"leads":[19],"to":[20,79,94,109,126],"less":[21],"understanding":[22],"about":[23],"their":[24],"decision":[25],"processes.":[26],"Therefore,":[27],"introspection":[28,74,108,145],"techniques":[29,75,146],"been":[31],"proposed,":[32],"mostly":[33],"for":[34,58,130,147],"images":[35,44],"as":[36],"input":[37],"data.":[38],"Patterns":[39],"or":[40],"relevant":[41],"regions":[42],"can":[45],"be":[46],"intuitively":[47],"interpreted":[48],"by":[49],"a":[50,91,123],"human":[51],"observer.":[52],"This":[53],"is":[54],"not":[55],"case":[57],"more":[59],"complex":[60],"data":[61,141],"like":[62],"speech":[63],"recordings.":[64],"In":[65],"this":[66,87],"work,":[67],"we":[68,89,115],"investigate":[69],"application":[71],"common":[73],"from":[76,100,139],"computer":[77],"vision":[78],"an":[80],"Automatic":[81],"Speech":[82],"Recognition":[83],"(ASR)":[84],"task.":[85],"To":[86,111],"end,":[88],"use":[90],"model":[92],"similar":[93],"image":[95,107],"classification,":[96],"which":[97],"predicts":[98],"letters":[99],"spectrograms.":[101],"We":[102,152],"show":[103],"difficulties":[104],"applying":[106],"ASR.":[110],"tackle":[112],"problems,":[114],"propose":[116],"normalized":[117],"averaging":[118],"aligned":[120],"inputs":[121],"(NAvAI):":[122],"data-driven":[124],"method":[125,136,156],"reveal":[127],"learned":[128],"patterns":[129,162],"prediction":[131],"specific":[133],"classes.":[134],"Our":[135],"integrates":[137],"information":[138],"many":[140],"examples":[142],"through":[143],"local":[144],"Convolutional":[148],"(CNNs).":[151],"demonstrate":[153],"that":[154],"our":[155],"provides":[157],"better":[158],"interpretability":[159],"letter-specific":[161],"than":[163],"existing":[164],"methods.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}