{"id":"https://openalex.org/W2498338956","doi":"https://doi.org/10.21437/odyssey.2016-17","title":"On the use of phone-gram units in recurrent neural networks for language identification","display_name":"On the use of phone-gram units in recurrent neural networks for language identification","publication_year":2016,"publication_date":"2016-06-21","ids":{"openalex":"https://openalex.org/W2498338956","doi":"https://doi.org/10.21437/odyssey.2016-17","mag":"2498338956"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2016-17","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2016-17","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2016)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://oa.upm.es/47224/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082214856","display_name":"Christian Salamea","orcid":"https://orcid.org/0000-0002-5243-5714"},"institutions":[{"id":"https://openalex.org/I3132940433","display_name":"Politecnica Salesiana University","ror":"https://ror.org/00f11af73","country_code":"EC","type":"education","lineage":["https://openalex.org/I3132940433"]}],"countries":["EC"],"is_corresponding":true,"raw_author_name":"Christian Salamea","raw_affiliation_strings":["Universidad Polit\u00e9cnica Salesiana del Ecuador Calle Vieja 12-30 y Elia Liut, Casilla 26, Cuenca, Ecuador","Speech Technology Group. Dpto. de Ing. Electr\u00f3nica. Universidad Polit\u00e9cnica de Madrid. Ciudad Universitaria s/n 28040, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica Salesiana del Ecuador Calle Vieja 12-30 y Elia Liut, Casilla 26, Cuenca, Ecuador","institution_ids":["https://openalex.org/I3132940433"]},{"raw_affiliation_string":"Speech Technology Group. Dpto. de Ing. Electr\u00f3nica. Universidad Polit\u00e9cnica de Madrid. Ciudad Universitaria s/n 28040, Madrid, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024161267","display_name":"Luis Fernando D\u2019Haro","orcid":"https://orcid.org/0000-0002-3411-7384"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Luis Fernando D'Haro","raw_affiliation_strings":["Human Language Technology Institute for Infocomm Reseach (A-STAR) 1 Fusionopolis Way, #21-01 Singapore 138632"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Institute for Infocomm Reseach (A-STAR) 1 Fusionopolis Way, #21-01 Singapore 138632","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067867302","display_name":"Ricardo de C\u00f3rdoba","orcid":"https://orcid.org/0000-0002-7136-9636"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ricardo Cordoba","raw_affiliation_strings":["Speech Technology Group. Dpto. de Ing. Electr\u00f3nica. Universidad Polit\u00e9cnica de Madrid. Ciudad Universitaria s/n 28040, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Speech Technology Group. Dpto. de Ing. Electr\u00f3nica. Universidad Polit\u00e9cnica de Madrid. Ciudad Universitaria s/n 28040, Madrid, Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002427610","display_name":"Rub\u00e9n San-Segundo","orcid":"https://orcid.org/0000-0001-9659-5464"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rub\u00e9n San-Segundo","raw_affiliation_strings":["Speech Technology Group. Dpto. de Ing. Electr\u00f3nica. Universidad Polit\u00e9cnica de Madrid. Ciudad Universitaria s/n 28040, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Speech Technology Group. Dpto. de Ing. Electr\u00f3nica. Universidad Polit\u00e9cnica de Madrid. Ciudad Universitaria s/n 28040, Madrid, Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082214856"],"corresponding_institution_ids":["https://openalex.org/I3132940433"],"apc_list":null,"apc_paid":null,"fwci":3.8563,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.94275676,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"117","last_page":"123"},"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":0.9994999766349792,"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":0.9983000159263611,"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":0.7051059007644653},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6860244274139404},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.6701027154922485},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5961482524871826},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5244691371917725},{"id":"https://openalex.org/keywords/gram","display_name":"Gram","score":0.5161391496658325},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4266129434108734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41031548380851746},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.393512487411499},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.26987341046333313},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11636623740196228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7051059007644653},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6860244274139404},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6701027154922485},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5961482524871826},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5244691371917725},{"id":"https://openalex.org/C161369605","wikidata":"https://www.wikidata.org/wiki/Q41803","display_name":"Gram","level":3,"score":0.5161391496658325},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4266129434108734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41031548380851746},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.393512487411499},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26987341046333313},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11636623740196228},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/odyssey.2016-17","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2016-17","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2016)","raw_type":"proceedings-article"},{"id":"pmh:oai:oa.upm.es:47224","is_oa":true,"landing_page_url":"https://oa.upm.es/47224/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196323","display_name":"UPM Digital Archive (Technical University of Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I88060688","host_organization_name":"Universidad Polit\u00e9cnica de Madrid","host_organization_lineage":["https://openalex.org/I88060688"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of The Speaker and Language Recognition Workshop, Odyssey 2016 | Odyssey 2016: The Speaker and Language Recognition Workshop | 21/06/2016 - 24/06/2016 | Bilbao - Espa\u00f1a","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:oa.upm.es:47224","is_oa":true,"landing_page_url":"https://oa.upm.es/47224/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196323","display_name":"UPM Digital Archive (Technical University of Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I88060688","host_organization_name":"Universidad Polit\u00e9cnica de Madrid","host_organization_lineage":["https://openalex.org/I88060688"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of The Speaker and Language Recognition Workshop, Odyssey 2016 | Odyssey 2016: The Speaker and Language Recognition Workshop | 21/06/2016 - 24/06/2016 | Bilbao - Espa\u00f1a","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.7799999713897705,"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":21,"referenced_works":["https://openalex.org/W100623710","https://openalex.org/W179875071","https://openalex.org/W1591801644","https://openalex.org/W1970481385","https://openalex.org/W2038262612","https://openalex.org/W2097927681","https://openalex.org/W2100714283","https://openalex.org/W2131744502","https://openalex.org/W2148154194","https://openalex.org/W2150355110","https://openalex.org/W2158195707","https://openalex.org/W2168561756","https://openalex.org/W2172287020","https://openalex.org/W2406392101","https://openalex.org/W2474824677","https://openalex.org/W2560354942","https://openalex.org/W2915356350","https://openalex.org/W2950075229","https://openalex.org/W4233906699","https://openalex.org/W4307613132","https://openalex.org/W4385822273"],"related_works":["https://openalex.org/W2906970013","https://openalex.org/W3126081632","https://openalex.org/W2088254117","https://openalex.org/W4254593385","https://openalex.org/W2790582133","https://openalex.org/W2133946991","https://openalex.org/W1901380241","https://openalex.org/W2061937230","https://openalex.org/W2789473152","https://openalex.org/W3132255358"],"abstract_inverted_index":{"In":[0,23],"this":[1],"paper":[2],"we":[3],"present":[4],"our":[5,82,92],"results":[6],"on":[7,13],"using":[8,18,46],"RNN-based":[9],"LM":[10],"scores":[11,107,114],"trained":[12],"different":[14,19],"phone-gram":[15],"orders":[16],"and":[17,30,85,110,120],"phonetic":[20],"ASR":[21],"recognizers.":[22],"order":[24],"to":[25,31,55,81,136],"avoid":[26],"data":[27],"sparseness":[28],"problems":[29],"reduce":[32],"the":[33,57,72,76,86,99,104,137],"vocabulary":[34],"of":[35,59,88],"all":[36],"possible":[37],"n-gram":[38],"combinations,":[39],"a":[40,50,121],"K-means":[41],"clustering":[42,83],"procedure":[43],"was":[44],"performed":[45],"phone-vector":[47],"embeddings":[48],"as":[49],"pre-processing":[51],"step.":[52],"Additional":[53],"experiments":[54],"optimize":[56],"amount":[58],"classes,":[60],"batch-size,":[61],"hidden":[62],"neurons,":[63],"state-unfolding,":[64],"are":[65,108],"also":[66],"presented.":[67],"We":[68],"have":[69],"worked":[70],"with":[71,112],"KALAKA-3":[73],"database":[74],"for":[75],"plenty-closed":[77],"condition":[78],"[1].":[79],"Thanks":[80],"technique":[84],"combination":[87],"high":[89],"level":[90],"phonegrams,":[91],"phonotactic":[93],"system":[94,119],"performs":[95],"~13%":[96],"better":[97],"than":[98],"unigram-based":[100],"RNNLM":[101,106],"system.":[102,124,139],"Also,":[103],"obtained":[105],"calibrated":[109],"fused":[111],"other":[113],"from":[115],"an":[116],"acoustic-based":[117],"i-vector":[118],"traditional":[122],"PPRLM":[123],"This":[125],"fusion":[126],"provides":[127],"additional":[128],"improvements":[129],"showing":[130],"that":[131],"they":[132],"provide":[133],"complementary":[134],"information":[135],"LID":[138]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
