{"id":"https://openalex.org/W144981014","doi":"https://doi.org/10.21437/eurospeech.1999-97","title":"Multigrams for language identification","display_name":"Multigrams for language identification","publication_year":1999,"publication_date":"1999-09-05","ids":{"openalex":"https://openalex.org/W144981014","doi":"https://doi.org/10.21437/eurospeech.1999-97","mag":"144981014"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1999-97","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1999-97","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th European Conference on Speech Communication and Technology","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/A5056365527","display_name":"Stefan Harbeck","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Harbeck","raw_affiliation_strings":["University of Erlangen-Nuremberg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Erlangen-Nuremberg","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000077668","display_name":"Uwe Ohler","orcid":"https://orcid.org/0000-0002-0881-3116"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Uwe Ohler","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5622,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84351697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"375","last_page":"378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9957000017166138,"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/codebook","display_name":"Codebook","score":0.8947457075119019},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7820806503295898},{"id":"https://openalex.org/keywords/phonotactics","display_name":"Phonotactics","score":0.7805060148239136},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.770499050617218},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6913333535194397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6782051920890808},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6778312921524048},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6511408686637878},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6319699287414551},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5718929171562195},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.5388237237930298},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5241183042526245},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5012156963348389},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.4790800213813782},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.47487685084342957},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45211848616600037},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17843982577323914},{"id":"https://openalex.org/keywords/phonology","display_name":"Phonology","score":0.08462074398994446}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8947457075119019},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7820806503295898},{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.7805060148239136},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.770499050617218},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6913333535194397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6782051920890808},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6778312921524048},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6511408686637878},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6319699287414551},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5718929171562195},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5388237237930298},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5241183042526245},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5012156963348389},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.4790800213813782},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.47487685084342957},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45211848616600037},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17843982577323914},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.08462074398994446},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.1999-97","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1999-97","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th European Conference on Speech Communication and Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.18.2333","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.18.2333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www5.informatik.uni-erlangen.de/literature/ps-dir/1999/Harbeck99:MFL.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W68860800","https://openalex.org/W77717145","https://openalex.org/W192701511","https://openalex.org/W1530250655","https://openalex.org/W1533169541","https://openalex.org/W1555082340","https://openalex.org/W1607753411","https://openalex.org/W2097355338","https://openalex.org/W2134383396","https://openalex.org/W2172287020","https://openalex.org/W3036063182","https://openalex.org/W3144357634"],"related_works":["https://openalex.org/W3135356928","https://openalex.org/W4239391220","https://openalex.org/W1993768374","https://openalex.org/W2011110202","https://openalex.org/W2626486671","https://openalex.org/W2112664109","https://openalex.org/W2117325844","https://openalex.org/W4402218585","https://openalex.org/W2361504501","https://openalex.org/W2188983927"],"abstract_inverted_index":{"In":[0,28,70],"our":[1],"paper":[2],"we":[3,32,74,107],"present":[4],"two":[5],"new":[6,53],"approaches":[7],"for":[8,36,66],"language":[9],"identification.":[10],"Both":[11],"of":[12,19,39,82,86],"them":[13],"are":[14],"based":[15,25],"on":[16,102],"the":[17,29,52,67,71,80,83,87,93,97,103,118],"use":[18,33],"so-called":[20],"multigrams,":[21],"an":[22],"information":[23],"theoretic":[24],"observation":[26,54],"representation.":[27],"first":[30],"approach":[31,73,114,121],"multigram":[34,45],"models":[35],"phonotactic":[37],"modeling":[38],"phoneme":[40],"or":[41],"codebook":[42,120],"sequences.":[43],"The":[44],"model":[46],"can":[47],"be":[48],"used":[49],"to":[50,117],"segment":[51],"into":[55],"larger":[56],"units":[57],"(e.g.":[58],"something":[59],"like":[60],"words)":[61],"and":[62,101,126],"calculates":[63],"a":[64,76],"probability":[65],"best":[68,84],"segmentation.":[69],"second":[72,113],"build":[75],"fenon":[77],"recognizer":[78],"using":[79],"segments":[81],"segmentation":[85],"training":[88],"material":[89],"as":[90],""words"":[91],"inside":[92],"recognition":[94],"vocabulary.":[95],"On":[96],"OGI":[98],"test":[99],"corpus":[100,106],"NIST'95":[104],"evaluation":[105],"got":[108],"significant":[109],"improvements":[110],"with":[111],"this":[112],"in":[115],"comparison":[116],"unsupervised":[119],"when":[122],"discriminating":[123],"between":[124],"English":[125],"German":[127],"utterances.":[128]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}