{"id":"https://openalex.org/W2400735735","doi":"https://doi.org/10.1109/icassp.2016.7472824","title":"Investigating techniques for low resource conversational speech recognition","display_name":"Investigating techniques for low resource conversational speech recognition","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2400735735","doi":"https://doi.org/10.1109/icassp.2016.7472824","mag":"2400735735"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472824","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472824","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5025212823","display_name":"Antoine Laurent","orcid":"https://orcid.org/0000-0002-2653-1008"},"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":true,"raw_author_name":"Antoine Laurent","raw_affiliation_strings":["Vocapia Research, Orsay, France","Vocapia Research [Orsay] (3 rue Jean Rostand Parc Orsay Universit\u00e9 91400 Orsay - France)"],"affiliations":[{"raw_affiliation_string":"Vocapia Research, Orsay, France","institution_ids":["https://openalex.org/I99555447"]},{"raw_affiliation_string":"Vocapia Research [Orsay] (3 rue Jean Rostand Parc Orsay Universit\u00e9 91400 Orsay - France)","institution_ids":["https://openalex.org/I99555447"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045988326","display_name":"Thiago Fraga-Silva","orcid":"https://orcid.org/0009-0001-7928-8929"},"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":"Thiago Fraga-Silva","raw_affiliation_strings":["Vocapia Research, Orsay, France","Vocapia Research [Orsay] (3 rue Jean Rostand Parc Orsay Universit\u00e9 91400 Orsay - France)"],"affiliations":[{"raw_affiliation_string":"Vocapia Research, Orsay, France","institution_ids":["https://openalex.org/I99555447"]},{"raw_affiliation_string":"Vocapia Research [Orsay] (3 rue Jean Rostand Parc Orsay Universit\u00e9 91400 Orsay - France)","institution_ids":["https://openalex.org/I99555447"]}]},{"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/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]},{"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":"Lori Lamel","raw_affiliation_strings":["CNRS/LIMSI, Spoken Language Processing Group, Orsay Cedex, France","LIMSI - Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur (Universit\u00e9 Paris-Sud B\u00e2t. 507 - Rue du Belv\u00e9d\u00e8re -91405 ORSAY CEDEX - France)"],"affiliations":[{"raw_affiliation_string":"CNRS/LIMSI, Spoken Language Processing Group, Orsay Cedex, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LIMSI - Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur (Universit\u00e9 Paris-Sud B\u00e2t. 507 - Rue du Belv\u00e9d\u00e8re -91405 ORSAY CEDEX - France)","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I102197404"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109214406","display_name":"Jean\u2010Luc Gauvain","orcid":null},"institutions":[{"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"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Luc Gauvain","raw_affiliation_strings":["CNRS/LIMSI, Spoken Language Processing Group, Orsay Cedex, France","LIMSI - Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur (Universit\u00e9 Paris-Sud B\u00e2t. 507 - Rue du Belv\u00e9d\u00e8re -91405 ORSAY CEDEX - France)"],"affiliations":[{"raw_affiliation_string":"CNRS/LIMSI, Spoken Language Processing Group, Orsay Cedex, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LIMSI - Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur (Universit\u00e9 Paris-Sud B\u00e2t. 507 - Rue du Belv\u00e9d\u00e8re -91405 ORSAY CEDEX - France)","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I102197404"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025212823"],"corresponding_institution_ids":["https://openalex.org/I99555447"],"apc_list":null,"apc_paid":null,"fwci":1.2854,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.86498947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5975","last_page":"5979"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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":0.9986000061035156,"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":0.8651643991470337},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6343637108802795},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6341351866722107},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6037497520446777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5433353781700134},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5328434109687805},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5295126438140869},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5273491144180298},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5232592821121216},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4742545187473297},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4590844213962555},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4549216628074646},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28818804025650024}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8651643991470337},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6343637108802795},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6341351866722107},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6037497520446777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5433353781700134},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5328434109687805},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5295126438140869},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5273491144180298},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5232592821121216},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4742545187473297},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4590844213962555},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4549216628074646},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28818804025650024},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2016.7472824","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472824","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01515254v1","is_oa":false,"landing_page_url":"https://univ-lemans.hal.science/hal-01515254","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"www.icassp2016.org","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8399999737739563,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1555037511","https://openalex.org/W1604771987","https://openalex.org/W1965842648","https://openalex.org/W1975113979","https://openalex.org/W1993799394","https://openalex.org/W2000654171","https://openalex.org/W2016243284","https://openalex.org/W2052274902","https://openalex.org/W2056590938","https://openalex.org/W2091267617","https://openalex.org/W2091746061","https://openalex.org/W2106440210","https://openalex.org/W2292087804","https://openalex.org/W2294722231","https://openalex.org/W2397766809","https://openalex.org/W2406226915","https://openalex.org/W2407204023","https://openalex.org/W2407922671","https://openalex.org/W2442329935","https://openalex.org/W2594610113","https://openalex.org/W4285719527","https://openalex.org/W4300061183","https://openalex.org/W6635896687","https://openalex.org/W6696449567","https://openalex.org/W6712476315","https://openalex.org/W6713986472","https://openalex.org/W6714027799","https://openalex.org/W6718561954"],"related_works":["https://openalex.org/W2121652828","https://openalex.org/W2126322296","https://openalex.org/W2163537793","https://openalex.org/W4386794561","https://openalex.org/W2916997151","https://openalex.org/W2781555308","https://openalex.org/W3021690593","https://openalex.org/W2125343999","https://openalex.org/W4200200210","https://openalex.org/W2161188302"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"investigate":[4],"various":[5],"techniques":[6],"in":[7,33,106],"order":[8,34],"to":[9,13,35],"build":[10],"effective":[11],"speech":[12],"text":[14],"(STT)":[15],"and":[16,28,50],"keyword":[17],"search":[18],"(KWS)":[19],"systems":[20],"for":[21,65,102],"low":[22],"resource":[23],"conversational":[24],"speech.":[25],"Subword":[26],"decoding":[27],"graphemic":[29],"mappings":[30],"were":[31,54,63],"assessed":[32],"detect":[36],"out-of-vocabulary":[37],"keywords.":[38],"To":[39],"deal":[40],"with":[41,88],"the":[42,90,103,107,110],"limited":[43],"amount":[44],"of":[45,109],"transcribed":[46],"data,":[47],"semi-supervised":[48],"training":[49],"data":[51,61],"selection":[52],"methods":[53],"investigated.":[55],"Robust":[56],"acoustic":[57,66],"features":[58],"produced":[59],"via":[60],"augmentation":[62],"evaluated":[64],"modeling.":[67],"For":[68],"language":[69,105],"modeling,":[70],"automatically":[71],"retrieved":[72],"conversational-like":[73],"Webdata":[74],"was":[75],"used,":[76],"as":[77,79],"well":[78],"neural":[80],"network":[81],"based":[82],"models.":[83],"We":[84],"report":[85],"STT":[86],"improvements":[87],"all":[89],"techniques,":[91],"but":[92],"interestingly":[93],"only":[94],"some":[95],"improve":[96],"KWS":[97],"performance.":[98],"Results":[99],"are":[100],"reported":[101],"Swahili":[104],"context":[108],"2015":[111],"OpenKWS":[112],"Evaluation.":[113]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}
