{"id":"https://openalex.org/W2937780860","doi":"https://doi.org/10.1109/icassp.2019.8683706","title":"Sequence Noise Injected Training for End-to-end Speech Recognition","display_name":"Sequence Noise Injected Training for End-to-end Speech Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2937780860","doi":"https://doi.org/10.1109/icassp.2019.8683706","mag":"2937780860"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683706","pdf_url":null,"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":"conference-paper","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/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Research AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047353872","display_name":"Zolt\u00e1n T\u00fcske","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zoltan Tuske","raw_affiliation_strings":["IBM Research AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kartik Audhkhasi","raw_affiliation_strings":["IBM Research AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Research AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]}],"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":43,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6261","last_page":"6265"},"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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":0.7764928936958313},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7720197439193726},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6430445313453674},{"id":"https://openalex.org/keywords/telephony","display_name":"Telephony","score":0.6232845783233643},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6215059161186218},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5882348418235779},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5752196311950684},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5627801418304443},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.550207793712616},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5429965257644653},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5408028364181519},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5214528441429138},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.45184987783432007},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.42626190185546875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41922298073768616},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4140858054161072},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3390403091907501},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3109937012195587},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12545061111450195},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0777791440486908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764928936958313},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7720197439193726},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6430445313453674},{"id":"https://openalex.org/C195358072","wikidata":"https://www.wikidata.org/wiki/Q944584","display_name":"Telephony","level":2,"score":0.6232845783233643},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6215059161186218},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5882348418235779},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5752196311950684},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5627801418304443},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.550207793712616},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5429965257644653},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5408028364181519},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5214528441429138},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.45184987783432007},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.42626190185546875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41922298073768616},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4140858054161072},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3390403091907501},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3109937012195587},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12545061111450195},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0777791440486908},{"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683706","pdf_url":null,"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":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1855879034","https://openalex.org/W2000021165","https://openalex.org/W2013278460","https://openalex.org/W2025091773","https://openalex.org/W2057853719","https://openalex.org/W2057922125","https://openalex.org/W2079623482","https://openalex.org/W2096653978","https://openalex.org/W2111406701","https://openalex.org/W2127141656","https://openalex.org/W2160287763","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2545177271","https://openalex.org/W2735249812","https://openalex.org/W2749659443","https://openalex.org/W2765407302","https://openalex.org/W2782451907","https://openalex.org/W2889013998","https://openalex.org/W2899771611","https://openalex.org/W2916979304","https://openalex.org/W2962826786","https://openalex.org/W2963070863","https://openalex.org/W2963211739","https://openalex.org/W2963266252","https://openalex.org/W2963827914","https://openalex.org/W3037706425","https://openalex.org/W4211019631","https://openalex.org/W4285719527","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6653620104","https://openalex.org/W6713762819","https://openalex.org/W6728910023","https://openalex.org/W6735593169","https://openalex.org/W6745136726","https://openalex.org/W6747836893","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W1999699871","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W2145230572","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2146197305","https://openalex.org/W2166312020","https://openalex.org/W2033669961","https://openalex.org/W2134950286"],"abstract_inverted_index":{"We":[0,31],"present":[1],"a":[2,47,103],"simple":[3],"noise":[4],"injection":[5],"algorithm":[6],"for":[7,63,106],"training":[8,20],"end-to-end":[9],"ASR":[10],"models":[11,68,109],"which":[12],"consists":[13],"in":[14,75],"adding":[15],"to":[16,56,77],"the":[17,22,34,38,51,54,71,86,92],"spectra":[18,24],"of":[19,25,28,37,53],"utterances":[21,27,40,55],"scaled":[23],"random":[26],"comparable":[29],"length.":[30],"conjecture":[32],"that":[33,70],"sequence":[35],"information":[36],"\"noise\"":[39],"is":[41],"important":[42],"and":[43,66,88],"verify":[44],"this":[45,111],"via":[46],"contrast":[48],"experiment":[49],"where":[50],"frames":[52],"be":[57],"added":[58],"are":[59],"randomly":[60],"shuffled.":[61],"Experiments":[62],"both":[64],"CTC":[65],"attention-based":[67,107],"show":[69],"pro-posed":[72],"scheme":[73],"results":[74],"up":[76],"9%":[78],"relative":[79],"word":[80],"error":[81],"rate":[82],"improvements":[83],"(depending":[84],"on":[85,91,110],"model":[87],"test":[89],"set)":[90],"Switchboard":[93],"300":[94],"hours":[95],"English":[96],"conversational":[97],"telephony":[98],"database.":[99],"Additionally,":[100],"we":[101],"set":[102],"new":[104],"benchmark":[105],"encoder-decoder":[108],"corpus.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}