{"id":"https://openalex.org/W4225325590","doi":"https://doi.org/10.1109/icassp43922.2022.9746459","title":"Phonotactic Language Recognition Using A Universal Phoneme Recognizer and A Transformer Architecture","display_name":"Phonotactic Language Recognition Using A Universal Phoneme Recognizer and A Transformer Architecture","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225325590","doi":"https://doi.org/10.1109/icassp43922.2022.9746459"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746459","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5100679147","display_name":"David Romero","orcid":"https://orcid.org/0000-0003-0686-2341"},"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":"David Romero","raw_affiliation_strings":["Universidad Polit&#x00E9;cnica Salesiana,Interaction, Robotics and Automation Research Group,Cuenca,Ecuador"],"affiliations":[{"raw_affiliation_string":"Universidad Polit&#x00E9;cnica Salesiana,Interaction, Robotics and Automation Research Group,Cuenca,Ecuador","institution_ids":["https://openalex.org/I3132940433"]}]},{"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/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Luis Fernando D'Haro","raw_affiliation_strings":["Speech Technology and Machine Learning Group, Information and Telecommunication Center, Escuela &#x00E9; Superior de Ingenieros de Telecomunicaci&#x00F3;n, Universidad Polit\u00e9cnica de Madrid, Ciudad Universitaria Avda. Complutense, 30, 28040, Madrid"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Machine Learning Group, Information and Telecommunication Center, Escuela &#x00E9; Superior de Ingenieros de Telecomunicaci&#x00F3;n, Universidad Polit\u00e9cnica de Madrid, Ciudad Universitaria Avda. Complutense, 30, 28040, Madrid","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064788846","display_name":"Marcos Estecha-Garitagoitia","orcid":"https://orcid.org/0000-0001-8153-0182"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Marcos Estecha-Garitagoitia","raw_affiliation_strings":["Speech Technology Group, Information and Telecommunication Center, Universidad Polit\u00e9cnica de Madrid, Ciudad Universitaria Avda. Complutense, 30, 28040, Madrid"],"affiliations":[{"raw_affiliation_string":"Speech Technology Group, Information and Telecommunication Center, Universidad Polit\u00e9cnica de Madrid, Ciudad Universitaria Avda. Complutense, 30, 28040, Madrid","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"last","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":false,"raw_author_name":"Christian Salamea","raw_affiliation_strings":["Universidad Polit&#x00E9;cnica Salesiana,Interaction, Robotics and Automation Research Group,Cuenca,Ecuador"],"affiliations":[{"raw_affiliation_string":"Universidad Polit&#x00E9;cnica Salesiana,Interaction, Robotics and Automation Research Group,Cuenca,Ecuador","institution_ids":["https://openalex.org/I3132940433"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100679147"],"corresponding_institution_ids":["https://openalex.org/I3132940433"],"apc_list":null,"apc_paid":null,"fwci":0.5194,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.61349925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"1154","issue":null,"first_page":"6872","last_page":"6876"},"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":0.9998999834060669,"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/T10860","display_name":"Speech 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/phonotactics","display_name":"Phonotactics","score":0.867360532283783},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8175797462463379},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6716451644897461},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6501652002334595},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6419757604598999},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6148776412010193},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.598125159740448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5396103858947754},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4335300922393799},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.43207603693008423},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4285010099411011},{"id":"https://openalex.org/keywords/phonology","display_name":"Phonology","score":0.2415514588356018},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0900053083896637},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0734308660030365}],"concepts":[{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.867360532283783},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8175797462463379},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6716451644897461},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6501652002334595},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6419757604598999},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6148776412010193},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.598125159740448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5396103858947754},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4335300922393799},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.43207603693008423},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4285010099411011},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.2415514588356018},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0900053083896637},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0734308660030365},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746459","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W61053364","https://openalex.org/W1522301498","https://openalex.org/W1603959384","https://openalex.org/W2146194791","https://openalex.org/W2161723943","https://openalex.org/W2172287020","https://openalex.org/W2190173116","https://openalex.org/W2231567078","https://openalex.org/W2340176088","https://openalex.org/W2498338956","https://openalex.org/W2525778437","https://openalex.org/W2735439328","https://openalex.org/W2807627734","https://openalex.org/W2888821917","https://openalex.org/W2896457183","https://openalex.org/W2901219417","https://openalex.org/W2962784628","https://openalex.org/W2995728453","https://openalex.org/W3015468748","https://openalex.org/W3015877095","https://openalex.org/W3023815949","https://openalex.org/W3093931920","https://openalex.org/W3133593091","https://openalex.org/W4287704453","https://openalex.org/W4361745846","https://openalex.org/W4385245566","https://openalex.org/W6606123296","https://openalex.org/W6636133825","https://openalex.org/W6703974891","https://openalex.org/W6727690538","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6771847258","https://openalex.org/W6776048684","https://openalex.org/W6778016268","https://openalex.org/W6781533629","https://openalex.org/W7033271574"],"related_works":["https://openalex.org/W2615317726","https://openalex.org/W2021909761","https://openalex.org/W198649858","https://openalex.org/W2158491338","https://openalex.org/W2807901368","https://openalex.org/W2467354670","https://openalex.org/W2498910126","https://openalex.org/W2133733652","https://openalex.org/W2113687551","https://openalex.org/W2112752961"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"describe":[4],"a":[5,28,33],"phonotactic":[6],"language":[7,46],"recognition":[8],"model":[9],"that":[10,31,84,119],"effectively":[11],"manages":[12],"long":[13,43],"and":[14,42,54,63,65,87,108],"short":[15,41],"n-gram":[16,48],"input":[17],"sequences":[18],"to":[19,37,68,129],"learn":[20],"contextual":[21],"phonotactic-based":[22],"vector":[23],"embeddings.":[24],"Our":[25],"approach":[26,122],"uses":[27],"transformer-based":[29],"encoder":[30],"integrates":[32],"sliding":[34],"window":[35],"attention":[36],"attempt":[38],"finding":[39],"discriminative":[40,73],"cooccurrences":[44],"of":[45,58,126],"dependent":[47],"phonetic":[49],"units.":[50],"We":[51,102],"then":[52],"evaluate":[53],"compare":[55],"the":[56,71,81,106,130,135],"use":[57],"different":[59],"phoneme":[60],"recognizers":[61],"(Brno":[62],"Allosaurus)":[64],"sub-unit":[66],"tokenizers":[67],"help":[69],"select":[70],"more":[72],"n-grams.":[74],"The":[75,115],"proposed":[76,121],"architecture":[77],"is":[78],"evaluated":[79],"using":[80,105],"Kalaka-3":[82],"database":[83],"contains":[85],"clean":[86],"noisy":[88],"audio":[89],"recordings":[90],"for":[91],"very":[92],"similar":[93],"languages":[94],"(i.e.":[95],"Iberian":[96],"languages,":[97],"e.g.,":[98],"Spanish,":[99],"Galician,":[100],"Catalan).":[101],"provide":[103],"results":[104,117],"Cavg":[107],"accuracy":[109],"metrics":[110],"used":[111],"in":[112,134],"NIST":[113],"evaluations.":[114],"experimental":[116],"show":[118],"our":[120],"outperforms":[123],"by":[124],"21%":[125],"relative":[127],"improvement":[128],"best":[131],"system":[132],"presented":[133],"Albayzin":[136],"LR":[137],"competition.":[138]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
