{"id":"https://openalex.org/W2963573574","doi":"https://doi.org/10.21437/interspeech.2017-588","title":"Acoustic Data-Driven Lexicon Learning Based on a Greedy Pronunciation Selection Framework","display_name":"Acoustic Data-Driven Lexicon Learning Based on a Greedy Pronunciation Selection Framework","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2963573574","doi":"https://doi.org/10.21437/interspeech.2017-588","mag":"2963573574"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-588","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-588","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/A5088378499","display_name":"Xiaohui Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Xiaohui Zhang","raw_affiliation_strings":["Center for Language and Speech Processing"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028956985","display_name":"Vimal Manohar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]},{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Vimal Manohar","raw_affiliation_strings":["Center for Language and Speech Processing","Human Language Technology Center of Excellence The Johns Hopkins University, Baltimore, MD 21218, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence The Johns Hopkins University, Baltimore, MD 21218, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Human Language Technology Center of Excellence The Johns Hopkins University, Baltimore, MD 21218, USA","Center for Language and Speech Processing"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence The Johns Hopkins University, Baltimore, MD 21218, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Center for Language and Speech Processing","Human Language Technology Center of Excellence The Johns Hopkins University, Baltimore, MD 21218, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence The Johns Hopkins University, Baltimore, MD 21218, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088378499"],"corresponding_institution_ids":["https://openalex.org/I4210098364"],"apc_list":null,"apc_paid":null,"fwci":0.195,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66721822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2541","last_page":"2545"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9926999807357788,"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":0.9919000267982483,"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/computer-science","display_name":"Computer science","score":0.8153969049453735},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.8068280220031738},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.78716641664505},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.680838406085968},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6019647121429443},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.5071642398834229},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48657500743865967},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4402669072151184},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13786068558692932},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09537363052368164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8153969049453735},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.8068280220031738},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.78716641664505},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.680838406085968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6019647121429443},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.5071642398834229},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48657500743865967},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4402669072151184},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13786068558692932},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09537363052368164},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2017-588","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-588","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":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2682542","https://openalex.org/W7052673","https://openalex.org/W1494198834","https://openalex.org/W1506752962","https://openalex.org/W1524333225","https://openalex.org/W1565662837","https://openalex.org/W1778492285","https://openalex.org/W1974974326","https://openalex.org/W2047497400","https://openalex.org/W2050526637","https://openalex.org/W2132991150","https://openalex.org/W2170353620","https://openalex.org/W2250357346","https://openalex.org/W2294752925","https://openalex.org/W2398867685","https://openalex.org/W2402146185","https://openalex.org/W2510428086","https://openalex.org/W2514741789"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2183593636"],"abstract_inverted_index":{"Speech":[0],"recognition":[1],"systems":[2],"for":[3,18,24,31,81],"irregularly-spelled":[4],"languages":[5],"like":[6],"English":[7],"normally":[8],"require":[9],"hand-written":[10],"pronunciations.In":[11],"this":[12],"paper,":[13],"we":[14,54,103],"describe":[15],"a":[16,66,108,114,137],"system":[17],"automatically":[19],"obtaining":[20],"pronunciations":[21,26],"of":[22,50,59,99,120],"words":[23],"which":[25,32,110],"are":[27,104],"not":[28,76],"available,":[29],"but":[30],"transcribed":[33],"data":[34],"exists.Our":[35],"method":[36],"integrates":[37],"information":[38],"from":[39,44,64],"the":[40,45,51,57,91],"letter":[41],"sequence":[42],"and":[43,126],"acoustic":[46],"evidence.The":[47],"novel":[48],"aspect":[49],"problem":[52,58],"that":[53],"address":[55],"is":[56,127],"how":[60],"to":[61,78,106,113],"prune":[62],"entries":[63,74],"such":[65],"lexicon":[67,98,109,117],"(since,":[68],"empirically,":[69],"lexicons":[70,130],"with":[71,90,95,136],"too":[72],"many":[73],"do":[75],"tend":[77],"be":[79],"good":[80],"ASR":[82,86],"performance).Experiments":[83],"on":[84,123,141],"various":[85],"tasks":[87],"show":[88],"that,":[89],"proposed":[92],"framework,":[93],"starting":[94],"an":[96],"initial":[97],"several":[100],"thousand":[101],"words,":[102],"able":[105],"learn":[107],"performs":[111],"close":[112],"full":[115],"expert":[116],"in":[118],"terms":[119],"WER":[121],"performance":[122],"test":[124],"data,":[125],"better":[128],"than":[129],"built":[131],"using":[132],"G2P":[133],"alone":[134],"or":[135],"pruning":[138],"criterion":[139],"based":[140],"pronunciation":[142],"probability.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}