{"id":"https://openalex.org/W2112711188","doi":"https://doi.org/10.1109/icassp.2008.4518693","title":"Discriminative training for improving letter-to-sound conversion performance","display_name":"Discriminative training for improving letter-to-sound conversion performance","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2112711188","doi":"https://doi.org/10.1109/icassp.2008.4518693","mag":"2112711188"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518693","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5003997327","display_name":"Yi\u2010Ning Chen","orcid":"https://orcid.org/0000-0003-4821-8511"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi-Ning Chen","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft Research Asia, Beijing,"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing,","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014911461","display_name":"Peng Liu","orcid":"https://orcid.org/0000-0002-5926-3548"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Liu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft Research Asia, Beijing,"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing,","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101558681","display_name":"Jiali You","orcid":"https://orcid.org/0000-0002-0830-7088"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia-Li You","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft Research Asia, Beijing,"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing,","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank K. Soong","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft Research Asia, Beijing,"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing,","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003997327"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":0.3539,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.55211864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4649","last_page":"4652"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"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":0.9923999905586243,"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/discriminative-model","display_name":"Discriminative model","score":0.9518019556999207},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.8883002996444702},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7830654978752136},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7029744982719421},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.6396945118904114},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5877829790115356},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5861198902130127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5515265464782715},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44413647055625916},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3785248398780823},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35766634345054626},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11489975452423096},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06457412242889404}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9518019556999207},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8883002996444702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7830654978752136},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7029744982719421},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.6396945118904114},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5877829790115356},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5861198902130127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5515265464782715},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44413647055625916},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3785248398780823},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35766634345054626},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11489975452423096},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06457412242889404},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2008.4518693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518693","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W30564313","https://openalex.org/W44395966","https://openalex.org/W67332896","https://openalex.org/W109079948","https://openalex.org/W120415783","https://openalex.org/W156262465","https://openalex.org/W1506201763","https://openalex.org/W1506212051","https://openalex.org/W1508165687","https://openalex.org/W1779680350","https://openalex.org/W2005076803","https://openalex.org/W2033565080","https://openalex.org/W2075201173","https://openalex.org/W2109664771","https://openalex.org/W2113528982","https://openalex.org/W2156060302","https://openalex.org/W2158289097","https://openalex.org/W2302778528","https://openalex.org/W6630412972","https://openalex.org/W6676373471","https://openalex.org/W6677251380","https://openalex.org/W6682802244"],"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/W4391124013","https://openalex.org/W2153058382","https://openalex.org/W2080578089","https://openalex.org/W4387715848","https://openalex.org/W2179005426"],"abstract_inverted_index":{"In":[0,122],"this":[1],"paper,":[2],"we":[3,124,136],"propose":[4],"to":[5,72],"use":[6],"discriminative":[7,62,89,141],"training":[8],"(DT)":[9],"for":[10,26],"improving":[11],"letter-to-sound":[12],"(LTS)":[13],"conversion":[14],"performance.":[15],"LTS":[16],"is":[17],"a":[18,32,52,85,110,133,139],"critical":[19],"component":[20],"in":[21,36,69,84,132],"both":[22],"ASR":[23],"and":[24,97],"TTS":[25,40],"predicting":[27,42],"the":[28,37,43,74,82,129],"correct":[29],"pronunciation":[30,45],"of":[31,46,77,88],"word":[33],"not":[34],"included":[35],"lexicon.":[38],"For":[39],"applications,":[41],"proper":[44],"an":[47],"out-of-vocabulary":[48],"person/place":[49],"name,":[50],"especially":[51],"name":[53],"with":[54],"foreign":[55],"origin":[56],"can":[57,137],"be":[58],"challenging.":[59],"We":[60,80],"utilize":[61],"training,":[63],"which":[64],"has":[65],"been":[66],"successfully":[67],"used":[68],"speech":[70],"recognition,":[71],"sharpen":[73],"baseline":[75],"N-grams":[76],"grapheme-phoneme":[78],"pairs.":[79],"address":[81],"problem":[83],"unified":[86],"framework":[87],"training.":[90],"Two":[91],"criteria,":[92],"maximum":[93],"mutual":[94],"information":[95],"(MMI)":[96],"minimum":[98],"phoneme":[99],"error":[100,116],"(MPE),":[101],"are":[102],"investigated.":[103],"Experimental":[104],"results":[105],"show":[106],"that":[107,126],"DT":[108],"yields":[109],"small":[111],"(3.8-4.6%":[112],"relative)":[113],"but":[114],"consistent":[115],"reduction":[117],"across":[118],"all":[119],"databases":[120],"tested.":[121],"addition,":[123],"observe":[125],"by":[127],"pinpointing":[128],"local":[130],"errors":[131],"finer":[134],"resolution,":[135],"obtain":[138],"better":[140],"model.":[142]},"counts_by_year":[{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}