{"id":"https://openalex.org/W2026339097","doi":"https://doi.org/10.1109/icassp.2009.4960586","title":"Modeling characters versuswords for mandarin speech recognition","display_name":"Modeling characters versuswords for mandarin speech recognition","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2026339097","doi":"https://doi.org/10.1109/icassp.2009.4960586","mag":"2026339097"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 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/A5103087840","display_name":"Jun Luo","orcid":"https://orcid.org/0000-0002-1010-2954"},"institutions":[{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Jun Luo","raw_affiliation_strings":["Spoken Language Processing Group, CNRS-LIMSI, Orsay, France","Spoken Language Processing Group, CNRS-LIMSI, BP 133 91403 Orsay cedex, France"],"affiliations":[{"raw_affiliation_string":"Spoken Language Processing Group, CNRS-LIMSI, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Spoken Language Processing Group, CNRS-LIMSI, BP 133 91403 Orsay cedex, France","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062446882","display_name":"Lori Lamel","orcid":"https://orcid.org/0000-0001-7443-9938"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lori Lamel","raw_affiliation_strings":["Spoken Language Processing Group, CNRS-LIMSI, Orsay, France","Spoken Language Processing Group, CNRS-LIMSI, BP 133 91403 Orsay cedex, France"],"affiliations":[{"raw_affiliation_string":"Spoken Language Processing Group, CNRS-LIMSI, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Spoken Language Processing Group, CNRS-LIMSI, BP 133 91403 Orsay cedex, France","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109214406","display_name":"Jean\u2010Luc Gauvain","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Luc Gauvain","raw_affiliation_strings":["Spoken Language Processing Group, CNRS-LIMSI, Orsay, France","Spoken Language Processing Group, CNRS-LIMSI, BP 133 91403 Orsay cedex, France"],"affiliations":[{"raw_affiliation_string":"Spoken Language Processing Group, CNRS-LIMSI, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Spoken Language Processing Group, CNRS-LIMSI, BP 133 91403 Orsay cedex, France","institution_ids":["https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103087840"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210115485"],"apc_list":null,"apc_paid":null,"fwci":3.4894,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.92720894,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4325","last_page":"4328"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.995199978351593,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8627773523330688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8252720236778259},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6889864802360535},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6756661534309387},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6352065205574036},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6285951137542725},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.614587128162384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6061278581619263},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5753484964370728},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.4886048436164856},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44210225343704224},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.28819313645362854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07911476492881775}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8627773523330688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252720236778259},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6889864802360535},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6756661534309387},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6352065205574036},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6285951137542725},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.614587128162384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6061278581619263},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5753484964370728},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.4886048436164856},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44210225343704224},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.28819313645362854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07911476492881775},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W60702959","https://openalex.org/W67810553","https://openalex.org/W1904457459","https://openalex.org/W1970689298","https://openalex.org/W1973200086","https://openalex.org/W2045628429","https://openalex.org/W2097927681","https://openalex.org/W2115390146","https://openalex.org/W2138436078","https://openalex.org/W2159948109","https://openalex.org/W2950186769"],"related_works":["https://openalex.org/W2374317326","https://openalex.org/W2990005675","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W1997182898","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Word":[0],"based":[1],"models":[2],"are":[3,70,130],"widely":[4],"used":[5],"in":[6,53,88,127],"speech":[7],"recognition":[8],"since":[9],"they":[10],"typically":[11],"perform":[12],"well.":[13],"However,":[14],"the":[15,33,111,133],"question":[16],"of":[17],"whether":[18],"it":[19],"is":[20,39,51,104],"better":[21],"to":[22,58,72,75,106,117,124],"use":[23],"a":[24,27,47,54,60,125],"word-based":[25,61,94,102],"or":[26,44],"character-based":[28,96,108],"model":[29],"warrants":[30],"being":[31],"for":[32,132],"Mandarin":[34,135],"Chinese":[35,38,64],"language.":[36],"Since":[37],"written":[40],"without":[41],"any":[42],"spaces":[43],"word":[45,48],"delimiters,":[46],"segmentation":[49],"algorithm":[50],"applied":[52],"pre-processing":[55],"step":[56],"prior":[57],"training":[59],"language":[62],"model.":[63],"characters":[65,74],"carry":[66],"meaning":[67],"and":[68,95,98],"speakers":[69],"free":[71],"combine":[73],"construct":[76],"new":[77],"words.":[78],"This":[79,90],"suggests":[80],"that":[81],"character":[82],"information":[83],"can":[84],"also":[85],"be":[86],"useful":[87],"communication.":[89],"paper":[91],"explores":[92],"both":[93],"models,":[97],"their":[99],"complementarity.":[100],"Although":[101],"modeling":[103],"found":[105],"outperform":[107],"modeling,":[109],"increasing":[110],"vocabulary":[112],"size":[113],"from":[114],"56":[115],"k":[116,119],"160":[118],"words":[120],"did":[121],"not":[122],"lead":[123],"gain":[126],"performance.":[128],"Results":[129],"reported":[131],"Gale":[134],"speech-to-text":[136],"task.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}