{"id":"https://openalex.org/W3131305672","doi":"https://doi.org/10.1109/icassp39728.2021.9414027","title":"An Investigation of End-to-End Models for Robust Speech Recognition","display_name":"An Investigation of End-to-End Models for Robust Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3131305672","doi":"https://doi.org/10.1109/icassp39728.2021.9414027","mag":"3131305672"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.06237","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039920828","display_name":"Archiki Prasad","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Archiki Prasad","raw_affiliation_strings":["Indian Institute of Technology Bombay","Indian Institute of Technology Bombay,Dept. of Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"Indian Institute of Technology Bombay,Dept. of Electrical Engineering","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036738038","display_name":"Preethi Jyothi","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Preethi Jyothi","raw_affiliation_strings":["Indian Institute of Technology Bombay","Indian Institute of Technology Bombay, Department of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"Indian Institute of Technology Bombay, Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103090020","display_name":"Rajbabu Velmurugan","orcid":"https://orcid.org/0000-0002-3511-1806"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajbabu Velmurugan","raw_affiliation_strings":["Indian Institute of Technology Bombay","Indian Institute of Technology Bombay,Dept. of Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"Indian Institute of Technology Bombay,Dept. of Electrical Engineering","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6893","last_page":"6897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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":0.7977995276451111},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7326484322547913},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6558069586753845},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6135409474372864},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6036959290504456},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5949079990386963},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5068255066871643},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43819302320480347},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40405383706092834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3873639404773712},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2056017816066742},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09506502747535706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7977995276451111},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7326484322547913},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6558069586753845},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6135409474372864},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6036959290504456},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5949079990386963},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5068255066871643},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43819302320480347},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40405383706092834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3873639404773712},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2056017816066742},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09506502747535706},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.06237","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.06237","pdf_url":"https://arxiv.org/pdf/2102.06237","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3131305672","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.06237.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":"doi:10.48550/arxiv.2102.06237","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.06237","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/srqw-yd05","is_oa":true,"landing_page_url":"https://doi.org/10.17023/srqw-yd05","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.06237","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.06237","pdf_url":"https://arxiv.org/pdf/2102.06237","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7599999904632568,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3131305672.pdf","grobid_xml":"https://content.openalex.org/works/W3131305672.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2033875152","https://openalex.org/W2042141988","https://openalex.org/W2062164080","https://openalex.org/W2193413348","https://openalex.org/W2219249508","https://openalex.org/W2587717635","https://openalex.org/W2618099328","https://openalex.org/W2696967604","https://openalex.org/W2885724687","https://openalex.org/W2950333269","https://openalex.org/W2963341071","https://openalex.org/W2963364041","https://openalex.org/W2963826681","https://openalex.org/W2972320711","https://openalex.org/W2973188947","https://openalex.org/W3015411292","https://openalex.org/W3034273309","https://openalex.org/W3097945073","https://openalex.org/W3209141406","https://openalex.org/W4232282348","https://openalex.org/W6639480849","https://openalex.org/W6687566353","https://openalex.org/W6688816777","https://openalex.org/W6763837741"],"related_works":["https://openalex.org/W3163142165","https://openalex.org/W3186546663","https://openalex.org/W2124338691","https://openalex.org/W3031135612","https://openalex.org/W3209376089","https://openalex.org/W3199713199","https://openalex.org/W2972592847","https://openalex.org/W2963321191","https://openalex.org/W2935938411","https://openalex.org/W3094225009","https://openalex.org/W3180992661","https://openalex.org/W141701120","https://openalex.org/W1504449689","https://openalex.org/W2892204792","https://openalex.org/W3011500442","https://openalex.org/W2572023240","https://openalex.org/W2152305730","https://openalex.org/W2964182350","https://openalex.org/W2963954250","https://openalex.org/W3116834994"],"abstract_inverted_index":{"End-to-end":[0],"models":[1],"for":[2,65,101],"robust":[3,67,102],"automatic":[4],"speech":[5,26,28,45,84,123,133],"recognition":[6],"(ASR)":[7],"have":[8],"not":[9,70],"been":[10,71],"sufficiently":[11],"well-explored":[12],"in":[13],"prior":[14],"work.":[15],"With":[16],"end-to-end":[17,66],"models,":[18],"one":[19],"could":[20],"choose":[21],"to":[22,41,53,55],"preprocess":[23],"the":[24,33,43,50,108,118,138,147,154],"input":[25,47],"using":[27,35],"enhancement":[29,134],"techniques":[30,86,92],"and":[31,48,78,87,98],"train":[32],"model":[34,51],"enhanced":[36],"speech.":[37,57],"Another":[38],"alternative":[39],"is":[40,107],"pass":[42],"noisy":[44,56],"as":[46],"modify":[49],"architecture":[52],"adapt":[54],"A":[58],"systematic":[59],"comparison":[60,82],"of":[61,83,120,146,156],"these":[62],"two":[63],"approaches":[64],"ASR":[68],"has":[69],"attempted":[72],"before.":[73],"We":[74],"address":[75],"this":[76],"gap":[77],"present":[79],"a":[80,131],"detailed":[81],"enhancement-based":[85],"three":[88],"different":[89],"model-based":[90,139],"adaptation":[91,140,157],"covering":[93],"data":[94],"augmentation,":[95],"multi-task":[96],"learning,":[97],"adversarial":[99,105],"learning":[100,106],"ASR.":[103],"While":[104],"best-performing":[109],"technique":[110,135],"on":[111],"certain":[112],"noise":[113,129,149],"types,":[114,130],"it":[115],"comes":[116],"at":[117],"cost":[119],"degrading":[121],"clean":[122],"WER.":[124],"On":[125],"other":[126],"relatively":[127],"stationary":[128],"new":[132],"outperformed":[136],"all":[137],"techniques.":[141],"This":[142],"suggests":[143],"that":[144],"knowledge":[145],"underlying":[148],"type":[150],"can":[151],"meaningfully":[152],"inform":[153],"choice":[155],"technique.":[158]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}