{"id":"https://openalex.org/W2953525958","doi":"https://doi.org/10.21437/interspeech.2019-2339","title":"Towards Debugging Deep Neural Networks by Generating Speech Utterances","display_name":"Towards Debugging Deep Neural Networks by Generating Speech Utterances","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2953525958","doi":"https://doi.org/10.21437/interspeech.2019-2339","mag":"2953525958"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2339","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.03164","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064127061","display_name":"Bilal Soomro","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bilal Soomro","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048689678","display_name":"Anssi Kanervisto","orcid":"https://orcid.org/0000-0002-7479-4574"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anssi Kanervisto","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085404562","display_name":"Trung Ng\u00f4 Tr\u1ecdng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trung Ngo Trong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037259225","display_name":"Ville Hautam\u00e4ki","orcid":"https://orcid.org/0000-0002-5885-0003"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ville Hautam\u00e4ki","raw_affiliation_strings":["University of Eastern Finland"],"affiliations":[{"raw_affiliation_string":"University of Eastern Finland","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064127061"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06211195,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3213","last_page":"3217"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9970999956130981,"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":0.9968000054359436,"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":0.8272291421890259},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7271009087562561},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6674680113792419},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6167372465133667},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.590096116065979},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.5365450978279114},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5101869106292725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5084039568901062},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.49001064896583557},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42740046977996826},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33121606707572937}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8272291421890259},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7271009087562561},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6674680113792419},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6167372465133667},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.590096116065979},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5365450978279114},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5101869106292725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5084039568901062},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.49001064896583557},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42740046977996826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33121606707572937},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2019-2339","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.03164","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.03164","pdf_url":"https://arxiv.org/pdf/1907.03164","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2953525958","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.03164.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:erepo.uef.fi:123456789/8004","is_oa":false,"landing_page_url":"https://erepo.uef.fi/handle/123456789/8004","pdf_url":null,"source":{"id":"https://openalex.org/S4306402418","display_name":"UEF eRepo (University of Eastern Finland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I175532246","host_organization_name":"University of Eastern Finland","host_organization_lineage":["https://openalex.org/I175532246"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Artikkelit ja abstraktit tieteellisiss\u00e4 konferenssijulkaisuissa"},{"id":"doi:10.48550/arxiv.1907.03164","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.03164","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.03164","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.03164","pdf_url":"https://arxiv.org/pdf/1907.03164","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2953525958.pdf","grobid_xml":"https://content.openalex.org/works/W2953525958.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2033310064","https://openalex.org/W2127141656","https://openalex.org/W2150769028","https://openalex.org/W2184045248","https://openalex.org/W2190008860","https://openalex.org/W2253993278","https://openalex.org/W2407023693","https://openalex.org/W2500162720","https://openalex.org/W2519091744","https://openalex.org/W2589857635","https://openalex.org/W2797583228","https://openalex.org/W2890964092","https://openalex.org/W2898422183","https://openalex.org/W2963112418","https://openalex.org/W2963207607","https://openalex.org/W2963288440","https://openalex.org/W2963464195","https://openalex.org/W2963989815"],"related_works":["https://openalex.org/W2972324312","https://openalex.org/W2063689849","https://openalex.org/W2579158309","https://openalex.org/W2736447239","https://openalex.org/W2095547148","https://openalex.org/W2395043307","https://openalex.org/W2931781875","https://openalex.org/W2963684067","https://openalex.org/W1492383498","https://openalex.org/W2887499727","https://openalex.org/W2087368178","https://openalex.org/W2511548894","https://openalex.org/W2612122134","https://openalex.org/W2943513641","https://openalex.org/W2291725357","https://openalex.org/W2751522352","https://openalex.org/W2939862648","https://openalex.org/W2566781703","https://openalex.org/W2742195102","https://openalex.org/W2950523597"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNN)":[3],"are":[4,40],"able":[5],"to":[6,56,63,83,132,147],"successfully":[7],"process":[8],"and":[9,78,112],"classify":[10],"speech":[11,57,75,155],"utterances.":[12],"However,":[13],"understanding":[14,64],"the":[15,45,61,74,87,104,122,151],"reason":[16],"behind":[17],"a":[18,71],"classification":[19,31],"by":[20,109],"DNN":[21,66,152],"is":[22,33],"difficult.":[23],"One":[24],"such":[25],"debugging":[26],"method":[27,55],"used":[28,131,146],"with":[29,121],"image":[30],"DNNs":[32],"activation":[34,81,127,142],"maximization,":[35],"which":[36],"generates":[37],"example-images":[38],"that":[39,118],"classified":[41],"as":[42,60],"one":[43],"of":[44,53,106,124,135],"classes.":[46,137],"In":[47],"this":[48,54],"work,":[49],"we":[50,91],"evaluate":[51],"applicability":[52],"utterance":[58],"classifiers":[59],"means":[62],"what":[65],"\"listens":[67],"to\".":[68],"We":[69,102],"trained":[70,88],"classifier":[72],"using":[73,96],"command":[76],"corpus":[77],"then":[79],"use":[80],"maximization":[82,128,143],"pull":[84],"samples":[85,108],"from":[86,94],"model.":[89],"Then":[90],"synthesize":[92],"audio":[93],"features":[95],"WaveNet":[97],"vocoder":[98],"for":[99],"subjective":[100],"analysis.":[101],"measure":[103],"quality":[105],"generated":[107],"objective":[110],"measurements":[111],"crowd-sourced":[113],"human":[114],"evaluations.":[115],"Results":[116],"show":[117],"when":[119],"combined":[120],"prior":[123],"natural":[125],"speech,":[126],"can":[129,144],"be":[130,145],"generate":[133],"examples":[134],"different":[136],"Based":[138],"on":[139],"these":[140],"results,":[141],"start":[148],"opening":[149],"up":[150],"black-box":[153],"in":[154],"tasks.":[156]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}