{"id":"https://openalex.org/W1974974326","doi":"https://doi.org/10.1109/asru.2013.6707759","title":"Acoustic data-driven pronunciation lexicon for large vocabulary speech recognition","display_name":"Acoustic data-driven pronunciation lexicon for large vocabulary speech recognition","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W1974974326","doi":"https://doi.org/10.1109/asru.2013.6707759","mag":"1974974326"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707759","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":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/2a9edeed-4e98-44ae-a421-c8514d5e3f41","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101607148","display_name":"Liang Lu","orcid":"https://orcid.org/0000-0003-4005-679X"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Liang Lu","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016623654","display_name":"Arnab Ghoshal","orcid":"https://orcid.org/0000-0003-1272-2599"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arnab Ghoshal","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101607148"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":8.8962,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.97489275,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"374","last_page":"379"},"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":0.9990000128746033,"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":0.9976999759674072,"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/lexicon","display_name":"Lexicon","score":0.9409065246582031},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.8835804462432861},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8535805344581604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6283617615699768},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6273964643478394},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.626173734664917},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.566254198551178},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.4849834442138672},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.43209195137023926},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.41530221700668335},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19131171703338623}],"concepts":[{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.9409065246582031},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8835804462432861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8535805344581604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6283617615699768},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6273964643478394},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.626173734664917},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.566254198551178},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.4849834442138672},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.43209195137023926},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.41530221700668335},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19131171703338623},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru.2013.6707759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707759","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:CiteSeerX.psu:10.1.1.395.9273","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.395.9273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2013/liang_asru13.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/2a9edeed-4e98-44ae-a421-c8514d5e3f41","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/2a9edeed-4e98-44ae-a421-c8514d5e3f41","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lu, L, Ghoshal, A & Renals, S 2013, Acoustic Data-driven Pronunciation Lexicon for Large Vocabulary Speech Recognition. in Automatic Speech Recognition and Understanding (ASRU), 2013 IEEE Workshop on. Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ASRU.2013.6707759","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/2a9edeed-4e98-44ae-a421-c8514d5e3f41","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/2a9edeed-4e98-44ae-a421-c8514d5e3f41","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/2a9edeed-4e98-44ae-a421-c8514d5e3f41","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/2a9edeed-4e98-44ae-a421-c8514d5e3f41","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lu, L, Ghoshal, A & Renals, S 2013, Acoustic Data-driven Pronunciation Lexicon for Large Vocabulary Speech Recognition. in Automatic Speech Recognition and Understanding (ASRU), 2013 IEEE Workshop on. Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ASRU.2013.6707759","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W7052673","https://openalex.org/W139772320","https://openalex.org/W1524333225","https://openalex.org/W1582482241","https://openalex.org/W1599512239","https://openalex.org/W1763005514","https://openalex.org/W1964917299","https://openalex.org/W1991180839","https://openalex.org/W1998653683","https://openalex.org/W2002342963","https://openalex.org/W2046932483","https://openalex.org/W2047497400","https://openalex.org/W2050526637","https://openalex.org/W2090755665","https://openalex.org/W2106554350","https://openalex.org/W2110842560","https://openalex.org/W2115900267","https://openalex.org/W2120209245","https://openalex.org/W2125234026","https://openalex.org/W2128022332","https://openalex.org/W2131342762","https://openalex.org/W2132714218","https://openalex.org/W2132991150","https://openalex.org/W2139406248","https://openalex.org/W2152731658","https://openalex.org/W2153058382","https://openalex.org/W2167655920","https://openalex.org/W2407897255","https://openalex.org/W6631362777","https://openalex.org/W6680871892"],"related_works":["https://openalex.org/W2506515307","https://openalex.org/W2060656088","https://openalex.org/W2183593636","https://openalex.org/W4391124013","https://openalex.org/W2080578089","https://openalex.org/W4387715848","https://openalex.org/W2179005426","https://openalex.org/W4287752972","https://openalex.org/W3037446006","https://openalex.org/W3037482713"],"abstract_inverted_index":{"Speech":[0],"recognition":[1],"systems":[2],"normally":[3],"use":[4],"handcrafted":[5,169],"pronunciation":[6,29],"lexicons":[7],"designed":[8],"by":[9],"linguistic":[10],"experts.":[11],"Building":[12],"and":[13,20,43,91,155],"maintaining":[14],"such":[15],"a":[16,28,39,114,148,152,158,167],"lexicon":[17,30,42,112,137,149],"is":[18,55,78,94],"expensive":[19],"time":[21],"consuming.":[22],"This":[23],"paper":[24],"concerns":[25],"automatically":[26],"learning":[27,138],"for":[31,63],"speech":[32,53],"recognition.":[33],"We":[34,59,98],"assume":[35],"the":[36,46,65,92,103,130,135,144],"availability":[37],"of":[38,48,68,106,116],"small":[40],"seed":[41,131],"then":[44],"learn":[45],"pronunciations":[47,67],"new":[49,69],"words":[50,70,127],"directly":[51],"from":[52,121],"that":[54,162,164],"transcribed":[56],"at":[57],"word-level.":[58],"present":[60],"two":[61],"implementations":[62],"refining":[64],"putative":[66],"based":[71,84],"on":[72,85,102],"acoustic":[73],"evidence.":[74],"The":[75,110],"first":[76],"one":[77],"an":[79],"expectation":[80],"maximization":[81],"(EM)":[82],"algorithm":[83],"weighted":[86],"finite":[87],"state":[88],"transducers":[89],"(WFSTs)":[90],"other":[93],"its":[95],"Viterbi":[96],"approximation.":[97],"carried":[99],"out":[100],"experiments":[101],"Switchboard":[104],"corpus":[105],"conversational":[107],"telephone":[108],"speech.":[109],"expert":[111],"has":[113],"size":[115],"more":[117],"than":[118],"30,000":[119],"words,":[120],"which":[122],"we":[123,140],"randomly":[124],"selected":[125],"5,000":[126],"to":[128],"form":[129],"lexicon.":[132,170],"By":[133],"using":[134,151,166],"proposed":[136],"method,":[139],"have":[141,156],"significantly":[142],"improved":[143],"accuracy":[145],"compared":[146],"with":[147],"learned":[150],"grapheme-to-phoneme":[153],"transformation,":[154],"obtained":[157],"word":[159],"error":[160],"rate":[161],"approaches":[163],"achieved":[165],"fully":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":8}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}