{"id":"https://openalex.org/W3106562331","doi":null,"title":"De-STT: De-entaglement of unwanted Nuisances and Biases in Speech to Text System using Adversarial Forgetting","display_name":"De-STT: De-entaglement of unwanted Nuisances and Biases in Speech to Text System using Adversarial Forgetting","publication_year":2020,"publication_date":"2020-11-25","ids":{"openalex":"https://openalex.org/W3106562331","mag":"3106562331"},"language":"en","primary_location":{"id":"mag:3106562331","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.12979","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.12979","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003400894","display_name":"Hemant N. Yadav","orcid":"https://orcid.org/0000-0003-3057-1456","observed_orcids":["https://orcid.org/0000-0003-3057-1456"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hemant Yadav","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3057-1456","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112584258","display_name":"Janvijay Singh","orcid":"https://orcid.org/0009-0000-0377-2610","observed_orcids":["https://orcid.org/0009-0000-0377-2610"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Janvijay Singh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062478344","display_name":"Atul Singh","orcid":"https://orcid.org/0000-0002-9263-7994","observed_orcids":["https://orcid.org/0000-0002-9263-7994"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atul Singh","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9263-7994","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058317628","display_name":"Rachit Mittal","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rachit Mittal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079357056","display_name":"Rajiv Ratn Shah","orcid":"https://orcid.org/0000-0003-1028-9373","observed_orcids":["https://orcid.org/0000-0003-1028-9373"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajiv Ratn Shah","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1028-9373","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":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":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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/T12031","display_name":"Speech and dialogue systems","score":0.0,"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/speech-to-text","display_name":"speech-to-text","score":0.843999981880188},{"id":"https://openalex.org/keywords/information-bottleneck","display_name":"information bottleneck","score":0.6830000281333923},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.6710000038146973},{"id":"https://openalex.org/keywords/speech-representation-learning","display_name":"speech representation learning","score":0.4690000116825104},{"id":"https://openalex.org/keywords/environmental-noise","display_name":"environmental noise","score":0.4399999976158142}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8811413049697876},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.8419891595840454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7436950206756592},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6958719491958618},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5545415878295898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5195651054382324},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4945659339427948},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4551941156387329},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4515185058116913},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34732478857040405},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12427306175231934},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.09092336893081665},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08902522921562195},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3106562331","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.12979","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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}],"best_oa_location":{"id":"mag:3106562331","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.12979","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W5524598","https://openalex.org/W184039015","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1731081199","https://openalex.org/W1882958252","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2405866807","https://openalex.org/W2408195107","https://openalex.org/W2607719644","https://openalex.org/W2885724687","https://openalex.org/W2944538127","https://openalex.org/W2953190524","https://openalex.org/W2962684181","https://openalex.org/W2972963519","https://openalex.org/W2995929068","https://openalex.org/W3015723617","https://openalex.org/W3028178035"],"related_works":["https://openalex.org/W3205626171","https://openalex.org/W7214790051","https://openalex.org/W3035049945","https://openalex.org/W4287270451","https://openalex.org/W7212285555","https://openalex.org/W7204479949","https://openalex.org/W4385823286","https://openalex.org/W3128798311","https://openalex.org/W4417126968","https://openalex.org/W4297841904"],"abstract_inverted_index":{"Training":[0],"a":[1,60],"robust":[2],"Speech":[3],"to":[4,42,66,77,112,116],"Text":[5],"(STT)":[6],"system":[7],"requires":[8],"tens":[9],"of":[10,12,14,39,81,131,162,176],"thousands":[11],"hours":[13],"data.":[15],"Variabilities":[16],"present":[17,145,184],"in":[18,146,185],"the":[19,37,79,83,87,114,147,153,165,181,186],"dataset":[20],"such":[21],"as":[22],"unwanted":[23,68],"nuisances":[24],"(environmental":[25],"noise,":[26],"etc)":[27,33],"and":[28,134],"biases":[29],"(accent,":[30],"gender,":[31],"age,":[32],"are":[34,138],"reasons":[35],"for":[36,51],"need":[38],"large":[40],"datasets":[41],"learn":[43,117],"general":[44,118],"representations,":[45],"which":[46],"is":[47],"often":[48],"not":[49,144],"feasible":[50],"low":[52],"resource":[53],"languages.":[54],"In":[55],"many":[56],"computer":[57],"vision":[58],"tasks,":[59],"recently":[61],"proposed":[62],"adversarial":[63,106,136,154],"forgetting":[64,155],"approach":[65],"remove":[67],"features":[69],"has":[70],"produced":[71],"good":[72],"results.":[73],"This":[74,108],"motivates":[75],"us":[76],"study":[78],"effect":[80],"de-entangling":[82],"accent":[84,119],"information":[85,101],"from":[86],"input":[88],"speech":[89,121],"signal":[90],"while":[91],"training":[92,109,148,167,187],"STT":[93,124],"systems.":[94],"To":[95],"this":[96],"end,":[97],"we":[98,170],"use":[99],"an":[100,158,173],"bottleneck":[102],"architecture":[103],"based":[104],"on":[105,127,140,180],"forgetting.":[107],"scheme":[110,156],"aims":[111],"enforce":[113],"model":[115],"invariant":[120],"representations.":[122],"Two":[123],"models":[125],"trained":[126],"just":[128],"20":[129],"hrs":[130],"audio,":[132],"with":[133,157],"without":[135],"forgetting,":[137],"tested":[139,179],"two":[141],"unseen":[142],"accents":[143,183],"set.":[149,188],"The":[150],"results":[151],"favour":[152],"absolute":[159,174],"average":[160],"improvement":[161,175],"6\\%":[163],"over":[164],"standard":[166],"scheme.":[168],"Furthermore,":[169],"also":[171],"observe":[172],"5.5\\%":[177],"when":[178],"seen":[182]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2020-12-07T00:00:00"}