{"id":"https://openalex.org/W2964012862","doi":"https://doi.org/10.21437/interspeech.2018-2456","title":"Multi-Modal Data Augmentation for End-to-end ASR","display_name":"Multi-Modal Data Augmentation for End-to-end ASR","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2964012862","doi":"https://doi.org/10.21437/interspeech.2018-2456","mag":"2964012862"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2456","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089603211","display_name":"Adithya Renduchintala","orcid":"https://orcid.org/0000-0002-1896-3679"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Adithya Renduchintala","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034588377","display_name":"Shuoyang Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuoyang Ding","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014455067","display_name":"Matthew Wiesner","orcid":"https://orcid.org/0000-0001-8653-7738"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Wiesner","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089603211"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":5.0623,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.96273522,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2394","last_page":"2398"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.992900013923645,"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/T12031","display_name":"Speech and dialogue systems","score":0.9904000163078308,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8326762914657593},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5727612972259521},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4857202172279358},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11356192827224731},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.10764971375465393},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.055036962032318115}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8326762914657593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5727612972259521},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4857202172279358},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11356192827224731},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.10764971375465393},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.055036962032318115}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2018-2456","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W3196421258","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2151749779","https://openalex.org/W2382290278","https://openalex.org/W2938107654"],"abstract_inverted_index":{"We":[0,47,82],"present":[1],"a":[2,51,92,125],"new":[3],"end-to-end":[4],"architecture":[5,26,50],"for":[6,32,37,96],"automatic":[7],"speech":[8,78],"recognition":[9],"(ASR)":[10],"that":[11],"can":[12,59],"be":[13],"trained":[14],"using":[15],"\\emph{symbolic}":[16],"input":[17,34,65],"in":[18],"addition":[19],"to":[20],"the":[21,42],"traditional":[22],"acoustic":[23,33],"input.":[24],"This":[25],"utilizes":[27],"two":[28],"separate":[29],"encoders:":[30],"one":[31],"and":[35,44,63,66,113,129],"another":[36],"symbolic":[38,93],"input,":[39],"both":[40,127],"sharing":[41],"attention":[43],"decoder":[45],"parameters.":[46],"call":[48],"this":[49],"multi-modal":[52,61],"data":[53],"augmentation":[54],"network":[55],"(MMDA),":[56],"as":[57,114,116],"it":[58],"support":[60],"(acoustic":[62],"symbolic)":[64],"enables":[67],"seamless":[68],"mixing":[69],"of":[70,86],"large":[71,88],"text":[72,89],"datasets":[73],"with":[74,128],"significantly":[75],"smaller":[76],"transcribed":[77],"corpora":[79,90],"during":[80],"training.":[81],"study":[83],"different":[84],"ways":[85],"transforming":[87],"into":[91],"form":[94],"suitable":[95],"training":[97],"our":[98],"MMDA":[99,103],"network.":[100],"Our":[101],"best":[102],"setup":[104],"obtains":[105],"small":[106],"improvements":[107],"on":[108],"character":[109],"error":[110,120],"rate":[111,121],"(CER),":[112],"much":[115],"7-10\\%":[117],"relative":[118],"word":[119],"(WER)":[122],"improvement":[123],"over":[124],"baseline":[126],"without":[130],"an":[131],"external":[132],"language":[133],"model.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":5}],"updated_date":"2026-03-08T06:56:09.383167","created_date":"2025-10-10T00:00:00"}