{"id":"https://openalex.org/W2939228015","doi":"https://doi.org/10.1109/icassp.2019.8683793","title":"Improving ASR Robustness to Perturbed Speech Using Cycle-consistent Generative Adversarial Networks","display_name":"Improving ASR Robustness to Perturbed Speech Using Cycle-consistent Generative Adversarial Networks","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2939228015","doi":"https://doi.org/10.1109/icassp.2019.8683793","mag":"2939228015"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683793","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683793","pdf_url":"https://ieeexplore.ieee.org/ielx7/8671773/8682151/08683793.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/8671773/8682151/08683793.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069966738","display_name":"Sri Harsha Dumpala","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sri Harsha Dumpala","raw_affiliation_strings":["TCS Research and Innovation, Mumbai, INDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research and Innovation, Mumbai, INDIA","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023803850","display_name":"Imran Sheikh","orcid":"https://orcid.org/0000-0001-5041-7398"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Imran Sheikh","raw_affiliation_strings":["TCS Research and Innovation, Mumbai, INDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research and Innovation, Mumbai, INDIA","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077689139","display_name":"Rupayan Chakraborty","orcid":"https://orcid.org/0000-0002-3566-0784"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rupayan Chakraborty","raw_affiliation_strings":["TCS Research and Innovation, Mumbai, INDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research and Innovation, Mumbai, INDIA","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047383705","display_name":"Sunil Kumar Kopparapu","orcid":"https://orcid.org/0000-0002-0502-527X"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sunil Kumar Kopparapu","raw_affiliation_strings":["TCS Research and Innovation, Mumbai, INDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research and Innovation, Mumbai, INDIA","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3338,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53502952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"52","issue":null,"first_page":"5726","last_page":"5730"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9979000091552734,"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/robustness","display_name":"Robustness (evolution)","score":0.8271684646606445},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7951667308807373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7923187017440796},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5301811695098877},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5136951208114624},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.49701669812202454},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.4695000648498535},{"id":"https://openalex.org/keywords/laughter","display_name":"Laughter","score":0.45804283022880554},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4437364935874939},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.42950040102005005},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3900880217552185}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8271684646606445},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7951667308807373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7923187017440796},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5301811695098877},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5136951208114624},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.49701669812202454},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.4695000648498535},{"id":"https://openalex.org/C2780775679","wikidata":"https://www.wikidata.org/wiki/Q170579","display_name":"Laughter","level":2,"score":0.45804283022880554},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4437364935874939},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.42950040102005005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3900880217552185},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683793","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683793","pdf_url":"https://ieeexplore.ieee.org/ielx7/8671773/8682151/08683793.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1109/icassp.2019.8683793","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683793","pdf_url":"https://ieeexplore.ieee.org/ielx7/8671773/8682151/08683793.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2939228015.pdf","grobid_xml":"https://content.openalex.org/works/W2939228015.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1523372075","https://openalex.org/W1969761120","https://openalex.org/W1998345532","https://openalex.org/W2042204882","https://openalex.org/W2053011040","https://openalex.org/W2123771434","https://openalex.org/W2125336414","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2288817436","https://openalex.org/W2331128040","https://openalex.org/W2339754110","https://openalex.org/W2471520273","https://openalex.org/W2517832688","https://openalex.org/W2567070169","https://openalex.org/W2586711829","https://openalex.org/W2593414223","https://openalex.org/W2747744257","https://openalex.org/W2774848319","https://openalex.org/W2916979304","https://openalex.org/W2951523806","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2963470893","https://openalex.org/W2964301649","https://openalex.org/W4293398859","https://openalex.org/W4320013936","https://openalex.org/W6621378261","https://openalex.org/W6631309588","https://openalex.org/W6702130928","https://openalex.org/W6730095352","https://openalex.org/W6731370813","https://openalex.org/W6746801104"],"related_works":["https://openalex.org/W2098265087","https://openalex.org/W1628467322","https://openalex.org/W2144256180","https://openalex.org/W2068323328","https://openalex.org/W2114887563","https://openalex.org/W1962303650","https://openalex.org/W2031585553","https://openalex.org/W3006284842","https://openalex.org/W4221146645","https://openalex.org/W2998458728"],"abstract_inverted_index":{"Naturally":[0],"introduced":[1],"perturbations":[2],"in":[3],"audio":[4],"signal,":[5],"caused":[6],"by":[7,88,117],"emotional":[8],"and":[9,48,67,74,114],"physical":[10],"states":[11],"of":[12,20,53,65,82,106,109,125],"the":[13,18,51,80,101,107,110,118,123],"speaker,":[14],"can":[15],"significantly":[16],"degrade":[17],"performance":[19,81],"Automatic":[21],"Speech":[22],"Recognition":[23],"(ASR)":[24],"systems.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29],"propose":[30],"a":[31],"front-end":[32,120],"based":[33,94],"on":[34,62,71],"Cycle-Consistent":[35],"Generative":[36],"Adversarial":[37],"Network":[38],"(CycleGAN)":[39],"which":[40],"transforms":[41],"naturally":[42],"perturbed":[43,66,103,112],"speech":[44,90,113],"into":[45],"normal":[46,68],"speech,":[47],"hence":[49],"improves":[50],"robustness":[52],"an":[54],"ASR":[55,85],"system.":[56],"The":[57],"CycleGAN":[58,93],"model":[59],"is":[60],"trained":[61],"non-parallel":[63],"examples":[64],"speech.":[69,104],"Experiments":[70],"spontaneous":[72],"laughter-speech":[73],"creaky":[75],"voice":[76],"datasets":[77],"show":[78],"that":[79],"four":[83],"different":[84],"systems":[86],"improve":[87],"using":[89,100],"obtained":[91],"from":[92],"front-end,":[95],"as":[96],"compared":[97],"to":[98],"directly":[99],"original":[102],"Visualization":[105],"features":[108],"laughter":[111],"those":[115],"generated":[116],"proposed":[119],"further":[121],"demonstrates":[122],"effectiveness":[124],"our":[126],"approach.":[127]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}