{"id":"https://openalex.org/W4221151563","doi":"https://doi.org/10.21437/interspeech.2022-821","title":"Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing","display_name":"Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4221151563","doi":"https://doi.org/10.21437/interspeech.2022-821"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-821","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-821","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5102014291","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0003-4865-1307"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":["IBM Research AI, IBM T. J. Watson Research Center, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, IBM T. J. Watson Research Center, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Research AI, IBM T. J. Watson Research Center, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, IBM T. J. Watson Research Center, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069028016","display_name":"Tohru Nagano","orcid":"https://orcid.org/0000-0002-3686-2791"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tohru Nagano","raw_affiliation_strings":["IBM Research Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028421346","display_name":"Masayuki Suzuki","orcid":"https://orcid.org/0000-0002-0436-1490"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayuki Suzuki","raw_affiliation_strings":["IBM Research Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101752582","display_name":"Takashi Fukuda","orcid":"https://orcid.org/0000-0003-1635-4471"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Fukuda","raw_affiliation_strings":["IBM Research Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Research AI, IBM T. J. Watson Research Center, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, IBM T. J. Watson Research Center, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Gakuto Kurata","raw_affiliation_strings":["IBM Research Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2638","last_page":"2642"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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/smoothing","display_name":"Smoothing","score":0.7642497420310974},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6654256582260132},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5909262895584106},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5905084609985352},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4834185838699341},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.4326803684234619},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.429690420627594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40400630235671997},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37581542134284973},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.293722540140152},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.10513725876808167},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08741217851638794},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08335623145103455}],"concepts":[{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.7642497420310974},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6654256582260132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5909262895584106},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5905084609985352},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4834185838699341},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.4326803684234619},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.429690420627594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40400630235671997},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37581542134284973},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.293722540140152},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.10513725876808167},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08741217851638794},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08335623145103455},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-821","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-821","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W1979651826","https://openalex.org/W2079623482","https://openalex.org/W2095705004","https://openalex.org/W2143612262","https://openalex.org/W2166637769","https://openalex.org/W2183341477","https://openalex.org/W2396384435","https://openalex.org/W2407080277","https://openalex.org/W2799800213","https://openalex.org/W2890297197","https://openalex.org/W2936774411","https://openalex.org/W2937780860","https://openalex.org/W2948210185","https://openalex.org/W2962760690","https://openalex.org/W2963587345","https://openalex.org/W2964081807","https://openalex.org/W2994884786","https://openalex.org/W3007227084","https://openalex.org/W3008037978","https://openalex.org/W3015190365","https://openalex.org/W3015889230","https://openalex.org/W3036585823","https://openalex.org/W3162512456","https://openalex.org/W3163300396","https://openalex.org/W3204494926","https://openalex.org/W4226315417","https://openalex.org/W4296068414","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W1978572805","https://openalex.org/W2383807498","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W4238188170","https://openalex.org/W2125114371","https://openalex.org/W2019977573","https://openalex.org/W2149980199","https://openalex.org/W3125766170","https://openalex.org/W2040641410"],"abstract_inverted_index":{"We":[0],"introduce":[1],"two":[2,78],"techniques,":[3],"length":[4,44],"perturbation":[5,26],"and":[6,35,87,115,131],"n-best":[7,74],"based":[8,50],"label":[9,51],"smoothing,":[10],"to":[11,41,56,64],"improve":[12,108],"generalization":[13,110],"of":[14,38,45,111],"deep":[15],"neural":[16,96],"network":[17,97],"(DNN)":[18],"acoustic":[19,100],"models":[20,101,113],"for":[21,102],"automatic":[22],"speech":[23,47],"recognition":[24],"(ASR).Length":[25],"is":[27],"a":[28,127],"data":[29],"augmentation":[30],"algorithm":[31],"that":[32,105],"randomly":[33,53],"drops":[34],"inserts":[36],"frames":[37],"an":[39,88],"utterance":[40],"alter":[42],"the":[43,46,68,82,109],"feature":[48],"sequence.N-best":[49],"smoothing":[52],"injects":[54],"noise":[55],"ground":[57],"truth":[58],"labels":[59,70],"during":[60],"training":[61],"in":[62],"order":[63],"avoid":[65],"overfitting,":[66],"where":[67],"noisy":[69],"are":[71],"generated":[72],"from":[73],"hypotheses.We":[75],"evaluate":[76],"these":[77],"techniques":[79,107],"extensively":[80],"on":[81,135],"300-hour":[83],"Switchboard":[84],"(SWB300)":[85],"dataset":[86,93],"in-house":[89],"500-hour":[90],"Japanese":[91],"(JPN500)":[92],"using":[94,137],"recurrent":[95],"transducer":[98],"(RNNT)":[99],"ASR.We":[103],"show":[104],"both":[106],"RNNT":[112,138],"individually":[114],"they":[116,122],"can":[117],"also":[118],"be":[119],"complementary.In":[120],"particular,":[121],"yield":[123],"good":[124],"improvements":[125],"over":[126],"strong":[128],"SWB300":[129,136],"baseline":[130],"give":[132],"state-of-art":[133],"performance":[134],"models.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}