{"id":"https://openalex.org/W2671240430","doi":"https://doi.org/10.1109/icassp.2017.7953266","title":"An investigation into language model data augmentation for low-resourced STT and KWS","display_name":"An investigation into language model data augmentation for low-resourced STT and KWS","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2671240430","doi":"https://doi.org/10.1109/icassp.2017.7953266","mag":"2671240430"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5072219329","display_name":"Guangpu Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guangpu Huang","raw_affiliation_strings":["LIMSI, Universit\u00e9 Paris-Saclay, Orsay Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIMSI, Universit\u00e9 Paris-Saclay, Orsay Cedex, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067994666","display_name":"Thiago Fraga da Silva","orcid":null},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thiago Fraga da Silva","raw_affiliation_strings":["LIMSI, Universit\u00e9 Paris-Saclay, Orsay Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIMSI, Universit\u00e9 Paris-Saclay, Orsay Cedex, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062446882","display_name":"Lori Lamel","orcid":"https://orcid.org/0000-0001-7443-9938"},"institutions":[{"id":"https://openalex.org/I99555447","display_name":"Vocapia Research (France)","ror":"https://ror.org/00606js28","country_code":"FR","type":"company","lineage":["https://openalex.org/I99555447"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lori Lamel","raw_affiliation_strings":["Vocapia Research, Orsay Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vocapia Research, Orsay Cedex, France","institution_ids":["https://openalex.org/I99555447"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109214406","display_name":"Jean\u2010Luc Gauvain","orcid":null},"institutions":[{"id":"https://openalex.org/I99555447","display_name":"Vocapia Research (France)","ror":"https://ror.org/00606js28","country_code":"FR","type":"company","lineage":["https://openalex.org/I99555447"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Luc Gauvain","raw_affiliation_strings":["Vocapia Research, Orsay Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vocapia Research, Orsay Cedex, France","institution_ids":["https://openalex.org/I99555447"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002166593","display_name":"Arseniy Gorin","orcid":null},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Arseniy Gorin","raw_affiliation_strings":["LIMSI, Universit\u00e9 Paris-Saclay, Orsay Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIMSI, Universit\u00e9 Paris-Saclay, Orsay Cedex, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025212823","display_name":"Antoine Laurent","orcid":"https://orcid.org/0000-0002-2653-1008"},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Laurent","raw_affiliation_strings":["LIMSI, Universit\u00e9 Paris-Saclay, Orsay Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIMSI, Universit\u00e9 Paris-Saclay, Orsay Cedex, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044770590","display_name":"Rasa Lileikyt\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Rasa Lileikyte","raw_affiliation_strings":["LIMSI, Universit\u00e9 Paris-Saclay, Orsay Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIMSI, Universit\u00e9 Paris-Saclay, Orsay Cedex, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210115485"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114735916","display_name":"Abdel Messouadi","orcid":null},"institutions":[{"id":"https://openalex.org/I99555447","display_name":"Vocapia Research (France)","ror":"https://ror.org/00606js28","country_code":"FR","type":"company","lineage":["https://openalex.org/I99555447"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Abdel Messouadi","raw_affiliation_strings":["Vocapia Research, Orsay Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vocapia Research, Orsay Cedex, France","institution_ids":["https://openalex.org/I99555447"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6921,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.73705541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5790","last_page":"5794"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.871477484703064},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7148662209510803},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6882466077804565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6674273610115051},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6377568244934082},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6344968676567078},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6200547218322754},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.618571400642395},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5702201128005981},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5683126449584961},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5221897959709167},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5056924819946289},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3008653521537781},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09125736355781555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.871477484703064},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7148662209510803},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6882466077804565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6674273610115051},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6377568244934082},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6344968676567078},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6200547218322754},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.618571400642395},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5702201128005981},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5683126449584961},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5221897959709167},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5056924819946289},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3008653521537781},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09125736355781555},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2017.7953266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01837171v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01837171","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE, Mar 2017, New Orleans, United States. pp.5790-5794, &#x27E8;10.1109/ICASSP.2017.7953266&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8122016617","display_name":"Speech And Language technologies for Security Applications","funder_award_id":"ANR-14-CE28-0021","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W132821814","https://openalex.org/W196214544","https://openalex.org/W309335912","https://openalex.org/W630532510","https://openalex.org/W1565198967","https://openalex.org/W1603342183","https://openalex.org/W1904457459","https://openalex.org/W2103361667","https://openalex.org/W2124807415","https://openalex.org/W2130437494","https://openalex.org/W2141599568","https://openalex.org/W2159948109","https://openalex.org/W2251892835","https://openalex.org/W2292087804","https://openalex.org/W2346259642","https://openalex.org/W2396672644","https://openalex.org/W2399344342","https://openalex.org/W2399715921","https://openalex.org/W2403657120","https://openalex.org/W2407420912","https://openalex.org/W2516354030","https://openalex.org/W2579873589","https://openalex.org/W4299951565","https://openalex.org/W6603931906","https://openalex.org/W6607974698","https://openalex.org/W6610777176","https://openalex.org/W6680890276","https://openalex.org/W6691564168","https://openalex.org/W6732226411"],"related_works":["https://openalex.org/W2160451571","https://openalex.org/W2463396630","https://openalex.org/W2495256954","https://openalex.org/W2259317772","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2129812225","https://openalex.org/W4290708361"],"abstract_inverted_index":{"This":[0],"paper":[1],"reports":[2],"on":[3,87,108],"investigations":[4],"using":[5,52],"two":[6],"techniques":[7],"for":[8,14],"language":[9,40],"model":[10,41],"text":[11],"data":[12],"augmentation":[13],"low-resourced":[15],"automatic":[16,88],"speech":[17],"recognition":[18],"and":[19,38,95,118,142],"keyword":[20,144],"search.":[21],"Lowresourced":[22],"languages":[23,110,126],"are":[24],"characterized":[25],"by":[26],"limited":[27],"training":[28],"materials,":[29],"which":[30,91],"typically":[31],"results":[32],"in":[33,111,135],"high":[34],"out-of-vocabulary":[35],"(OOV)":[36],"rates":[37],"poor":[39],"estimates.":[42],"One":[43],"technique":[44,84],"makes":[45],"use":[46],"of":[47,114,137],"recurrent":[48],"neural":[49],"networks":[50],"(RNNs)":[51],"word":[53,138],"or":[54],"subword":[55,71],"units.":[56],"Word-based":[57],"RNNs":[58],"keep":[59],"the":[60,68,75,102,112,115],"same":[61],"system":[62],"vocabulary,":[63],"so":[64],"they":[65],"cannot":[66],"reduce":[67,74],"OOV,":[69],"whereas":[70],"units":[72],"can":[73],"OOV":[76],"but":[77],"generate":[78],"many":[79],"false":[80],"combinations.":[81],"A":[82],"complementary":[83],"is":[85,96],"based":[86],"machine":[89],"translation,":[90],"requires":[92],"parallel":[93],"texts":[94],"able":[97],"to":[98,101],"add":[99],"words":[100],"vocabulary.":[103],"These":[104],"methods":[105],"were":[106,132],"assessed":[107],"10":[109],"context":[113],"Babel":[116],"program":[117],"NIST":[119],"OpenKWS":[120],"evaluation.":[121],"Although":[122],"improvements":[123],"vary":[124],"across":[125],"with":[127],"both":[128],"methods,":[129],"small":[130],"gains":[131],"generally":[133],"observed":[134],"terms":[136],"error":[139],"rate":[140],"reduction":[141],"improved":[143],"search":[145],"performance.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
