{"id":"https://openalex.org/W2170353620","doi":"https://doi.org/10.18653/v1/d13-1019","title":"Joint Learning of Phonetic Units and Word Pronunciations for ASR","display_name":"Joint Learning of Phonetic Units and Word Pronunciations for ASR","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2170353620","doi":"https://doi.org/10.18653/v1/d13-1019","mag":"2170353620"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d13-1019","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1019","pdf_url":"https://aclanthology.org/D13-1019.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/D13-1019.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047426349","display_name":"Chia-ying Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chia-ying Lee","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge , MA 02139 , USA","Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge , MA 02139 , USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433382","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0001-6183-0612"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge , MA 02139 , USA","Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge , MA 02139 , USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge , MA 02139 , USA","Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge , MA 02139 , USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"182","last_page":"192"},"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":0.9995999932289124,"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/T12031","display_name":"Speech and dialogue systems","score":0.9991999864578247,"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":0.8912009596824646},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.834606945514679},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.7436445951461792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6673555970191956},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6296384930610657},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.5410922169685364},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5323648452758789},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4830930233001709},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47700145840644836},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.44624584913253784},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08590474724769592}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8912009596824646},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.834606945514679},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7436445951461792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6673555970191956},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6296384930610657},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.5410922169685364},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5323648452758789},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4830930233001709},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47700145840644836},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.44624584913253784},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08590474724769592},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/d13-1019","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1019","pdf_url":"https://aclanthology.org/D13-1019.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.593.1464","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.593.1464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D13/D13-1019.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.648.1606","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.648.1606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://groups.csail.mit.edu/sls/publications/2013/Lee-Jackie_EMNLP-2013.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/d13-1019","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1019","pdf_url":"https://aclanthology.org/D13-1019.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2170353620.pdf","grobid_xml":"https://content.openalex.org/works/W2170353620.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W80018330","https://openalex.org/W605575788","https://openalex.org/W1510837697","https://openalex.org/W1918599710","https://openalex.org/W1957665339","https://openalex.org/W1964917299","https://openalex.org/W1990005915","https://openalex.org/W2045656233","https://openalex.org/W2050526637","https://openalex.org/W2078769636","https://openalex.org/W2090755665","https://openalex.org/W2099415988","https://openalex.org/W2100768664","https://openalex.org/W2111732304","https://openalex.org/W2117041980","https://openalex.org/W2125142492","https://openalex.org/W2130607791","https://openalex.org/W2132991226","https://openalex.org/W2148154194","https://openalex.org/W2158069733","https://openalex.org/W2401464865"],"related_works":["https://openalex.org/W2506515307","https://openalex.org/W2060656088","https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W4391124013","https://openalex.org/W2080578089","https://openalex.org/W2179005426","https://openalex.org/W1982818675"],"abstract_inverted_index":{"The":[0],"creation":[1],"of":[2,66,74,113],"a":[3,39,56,64],"pronunciation":[4,36],"lexicon":[5,103],"remains":[6],"the":[7,30,46,50,69,72,75,86,96,100,111],"most":[8],"inefficient":[9],"process":[10],"in":[11,55,84],"developing":[12],"an":[13,22],"Automatic":[14],"Speech":[15],"Recognizer":[16],"(ASR).In":[17],"this":[18],"paper,":[19],"we":[20],"propose":[21],"unsupervised":[23],"alternative":[24],"-requiring":[25],"no":[26],"language-specific":[27],"knowledge":[28],"-to":[29],"conventional":[31,118],"manual":[32],"approach":[33,110],"for":[34],"creating":[35],"dictionaries.We":[37],"present":[38],"hierarchical":[40],"Bayesian":[41],"model,":[42],"which":[43,85],"jointly":[44],"discovers":[45],"phonetic":[47,88],"inventory":[48,89],"and":[49,90,108],"Letter-to-Sound":[51],"(L2S)":[52],"mapping":[53],"rules":[54],"language":[57],"using":[58,117],"only":[59],"transcribed":[60],"data.When":[61],"tested":[62],"on":[63],"corpus":[65],"spontaneous":[67],"queries,":[68],"results":[70],"demonstrate":[71],"superiority":[73],"proposed":[76],"joint":[77],"learning":[78],"scheme":[79],"over":[80],"its":[81],"sequential":[82],"counterpart,":[83],"latent":[87],"L2S":[91],"mappings":[92],"are":[93],"learned":[94],"separately.Furthermore,":[95],"recognizers":[97,107],"built":[98],"with":[99],"automatically":[101],"induced":[102],"consistently":[104],"outperform":[105],"grapheme-based":[106],"even":[109],"performance":[112],"recognition":[114],"systems":[115],"trained":[116],"supervised":[119],"procedures.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}