{"id":"https://openalex.org/W2747090013","doi":"https://doi.org/10.21437/interspeech.2017-1262","title":"Leveraging Text Data for Word Segmentation for Underresourced Languages","display_name":"Leveraging Text Data for Word Segmentation for Underresourced Languages","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2747090013","doi":"https://doi.org/10.21437/interspeech.2017-1262","mag":"2747090013"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1262","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5034662562","display_name":"Thomas Glarner","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Thomas Glarner","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026448842","display_name":"Benedikt Boenninghoff","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benedikt Boenninghoff","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022949022","display_name":"Oliver Walter","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oliver Walter","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034662562"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9502,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.89563948,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2143","last_page":"2147"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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":0.8545188903808594},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6509274244308472},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.62227463722229},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6055439114570618},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5864090323448181},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.579785943031311},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5731759071350098},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5679113268852234},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5084596872329712},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4853612184524536},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4533998668193817},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.4425807595252991},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3419485092163086},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.19116821885108948},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.09050369262695312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8545188903808594},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6509274244308472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.62227463722229},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6055439114570618},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5864090323448181},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.579785943031311},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5731759071350098},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5679113268852234},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5084596872329712},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4853612184524536},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4533998668193817},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.4425807595252991},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3419485092163086},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.19116821885108948},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.09050369262695312},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2017-1262","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"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":20,"referenced_works":["https://openalex.org/W148837159","https://openalex.org/W1524333225","https://openalex.org/W1545920196","https://openalex.org/W2022058071","https://openalex.org/W2024490156","https://openalex.org/W2033413759","https://openalex.org/W2090755665","https://openalex.org/W2100768664","https://openalex.org/W2105016867","https://openalex.org/W2107240889","https://openalex.org/W2114347655","https://openalex.org/W2126377586","https://openalex.org/W2127498532","https://openalex.org/W2140991203","https://openalex.org/W2142390309","https://openalex.org/W2170353620","https://openalex.org/W2251711535","https://openalex.org/W2346964103","https://openalex.org/W2347098582","https://openalex.org/W2677604782"],"related_works":["https://openalex.org/W3126382579","https://openalex.org/W3107650560","https://openalex.org/W4315588616","https://openalex.org/W4317422773","https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2031284124","https://openalex.org/W2250993361","https://openalex.org/W2043781532"],"abstract_inverted_index":{"In":[0],"this":[1],"contribution":[2],"we":[3],"show":[4,110],"how":[5],"to":[6,10,44,52,57],"exploit":[7],"text":[8,38,104,119],"data":[9,61,120],"support":[11],"word":[12,33,91,123],"discovery":[13,81,92],"from":[14,49],"audio":[15,60],"input":[16],"in":[17],"an":[18,77],"underresourced":[19],"target":[20],"language.":[21],"Given":[22],"audio,":[23],"of":[24,67,114],"which":[25,94],"a":[26,46,68,83,90,98,127],"certain":[27],"amount":[28],"is":[29,42,72,95],"transcribed":[30],"at":[31],"the":[32,40,59,65,103,112,115,122],"level,":[34],"and":[35,54,89],"additional":[36],"unrelated":[37],"data,":[39],"approach":[41],"able":[43],"learn":[45],"probabilistic":[47],"mapping":[48],"acoustic":[50,79,86],"units":[51],"characters":[53],"utilize":[55],"it":[56],"segment":[58],"into":[62],"words":[63],"without":[64],"need":[66],"pronunciation":[69],"dictionary.":[70],"This":[71],"achieved":[73],"by":[74,126],"three":[75],"components:":[76],"unsupervised":[78],"unit":[80],"system,":[82,93],"supervisedly":[84],"trained":[85,101],"unit-to-grapheme":[87],"converter,":[88],"initialized":[96],"with":[97,118],"language":[99,116],"model":[100,117],"on":[102],"data.":[105],"Experiments":[106],"for":[107],"multiple":[108],"setups":[109],"that":[111],"initialization":[113],"improves":[121],"segementation":[124],"performance":[125],"large":[128],"margin.":[129]},"counts_by_year":[{"year":2018,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}