{"id":"https://openalex.org/W2022058071","doi":"https://doi.org/10.1109/asru.2013.6707761","title":"A hierarchical system for word discovery exploiting DTW-based initialization","display_name":"A hierarchical system for word discovery exploiting DTW-based initialization","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2022058071","doi":"https://doi.org/10.1109/asru.2013.6707761","mag":"2022058071"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","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/A5022949022","display_name":"Oliver Walter","orcid":null},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Oliver Walter","raw_affiliation_strings":["Department of Communications Engineering, University of Paderborn, Germany","[Department of Communication Engineering, University of Paderborn, Paderborn, Germany]"],"affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, University of Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]},{"raw_affiliation_string":"[Department of Communication Engineering, University of Paderborn, Paderborn, Germany]","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078472174","display_name":"Timo Korthals","orcid":"https://orcid.org/0000-0003-4297-7197"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Timo Korthals","raw_affiliation_strings":["Department of Communications Engineering, University of Paderborn, Germany","[Department of Communication Engineering, University of Paderborn, Paderborn, Germany]"],"affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, University of Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]},{"raw_affiliation_string":"[Department of Communication Engineering, University of Paderborn, Paderborn, Germany]","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":["Department of Communications Engineering, University of Paderborn, Germany","[Department of Communication Engineering, University of Paderborn, Paderborn, Germany]"],"affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, University of Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]},{"raw_affiliation_string":"[Department of Communication Engineering, University of Paderborn, Paderborn, Germany]","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113017615","display_name":"Bhiksha Raj","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhiksha Raj","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, United States","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, United States","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022949022"],"corresponding_institution_ids":["https://openalex.org/I206945453"],"apc_list":null,"apc_paid":null,"fwci":4.5001,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.9484548,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"386","last_page":"391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9988999962806702,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9965000152587891,"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":0.816848635673523},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7518736720085144},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7151833772659302},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6419315338134766},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6396632790565491},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6260464787483215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6093368530273438},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5954645276069641},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5535265207290649},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4975176155567169},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44858479499816895},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.43076157569885254},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14548450708389282},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11205661296844482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.816848635673523},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7518736720085144},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7151833772659302},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6419315338134766},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6396632790565491},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6260464787483215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6093368530273438},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5954645276069641},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5535265207290649},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4975176155567169},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44858479499816895},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.43076157569885254},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14548450708389282},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11205661296844482},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2013.6707761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:pub.librecat.org:2902861","is_oa":false,"landing_page_url":"https://pub.uni-bielefeld.de/record/2902861","pdf_url":null,"source":{"id":"https://openalex.org/S4306401671","display_name":"PUB \u2013 Publications at Bielefeld University (Bielefeld University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Walter O, Korthals T, Haeb-Umbach R, Raj B. A hierarchical system for word discovery exploiting DTW-based initialization. In:  <em>IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2013</em>. IEEE;  2013: 386-391.","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1574901103","https://openalex.org/W1967924372","https://openalex.org/W2025482506","https://openalex.org/W2073459066","https://openalex.org/W2078769636","https://openalex.org/W2095293504","https://openalex.org/W2114347655","https://openalex.org/W2127612600","https://openalex.org/W2140991203","https://openalex.org/W2166343746","https://openalex.org/W2277403007","https://openalex.org/W2396707013","https://openalex.org/W2401464865","https://openalex.org/W2407151108","https://openalex.org/W6668990524","https://openalex.org/W6678951767","https://openalex.org/W6712239252"],"related_works":["https://openalex.org/W3009759344","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944","https://openalex.org/W2523799048","https://openalex.org/W2155620340"],"abstract_inverted_index":{"Discovering":[0],"the":[1,25,34,38,60,65,85,93,108,111,114,117,141],"linguistic":[2],"structure":[3],"of":[4,47,67,72,110,113,119],"a":[5,68,76,99,120,154,162],"language":[6],"solely":[7],"from":[8,103],"spoken":[9,104],"input":[10,142],"asks":[11],"for":[12,56],"two":[13],"steps:":[14],"phonetic":[15],"and":[16,30],"lexical":[17],"discovery.":[18],"The":[19,50],"first":[20,61],"is":[21,129,133],"concerned":[22],"with":[23,80],"identifying":[24],"categorical":[26],"subword":[27,48,73,87],"unit":[28,88],"inventory":[29],"relating":[31],"it":[32,132],"to":[33,135,153],"underlying":[35],"acoustics,":[36],"while":[37],"second":[39],"aims":[40],"at":[41],"discovering":[42],"words":[43],"as":[44,131],"repeated":[45],"patterns":[46],"units.":[49],"hierarchical":[51],"approach":[52],"presented":[53],"here":[54],"accounts":[55],"classification":[57],"errors":[58],"in":[59,70,98,140,157],"stage":[62],"by":[63],"modelling":[64],"pronunciation":[66],"word":[69,115,158],"terms":[71],"units":[74],"probabilistically:":[75],"hidden":[77],"Markov":[78],"model":[79],"discrete":[81],"emission":[82],"probabilities,":[83],"emitting":[84],"observed":[86],"sequences.":[89],"We":[90],"describe":[91],"how":[92],"system":[94,128],"can":[95],"be":[96],"learned":[97],"completely":[100],"unsupervised":[101],"fashion":[102],"input.":[105],"To":[106],"improve":[107],"initialization":[109],"training":[112],"pronunciations,":[116],"output":[118],"dynamic":[121],"time":[122],"warping":[123],"based":[124],"acoustic":[125],"pattern":[126],"discovery":[127],"used,":[130],"able":[134],"discover":[136],"similar":[137],"temporal":[138],"sequences":[139],"data.":[143],"This":[144],"improved":[145],"initialization,":[146],"using":[147],"only":[148],"weak":[149],"supervision,":[150],"has":[151],"led":[152],"40%":[155],"reduction":[156],"error":[159],"rate":[160],"on":[161],"digit":[163],"recognition":[164],"task.":[165]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}