{"id":"https://openalex.org/W2121173708","doi":"https://doi.org/10.1109/icassp.2009.4960587","title":"Data-driven lexicon expansion for Mandarin broadcast news and conversation speech recognition","display_name":"Data-driven lexicon expansion for Mandarin broadcast news and conversation speech recognition","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2121173708","doi":"https://doi.org/10.1109/icassp.2009.4960587","mag":"2121173708"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960587","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/A5049457213","display_name":"Xin Lei","orcid":"https://orcid.org/0000-0002-4400-4068"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xin Lei","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396375","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-0356-1968"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["SRI International, Menlo Park, CA, US"],"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA, US","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["SRI International, Menlo Park, CA, US"],"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA, US","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049457213"],"corresponding_institution_ids":["https://openalex.org/I1298353152"],"apc_list":null,"apc_paid":null,"fwci":3.1614,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.92329448,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"5","issue":null,"first_page":"4329","last_page":"4332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9958000183105469,"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":0.9958000183105469,"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":0.9825999736785889,"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":0.9233999848365784,"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/pronunciation","display_name":"Pronunciation","score":0.909055769443512},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8322001695632935},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.8235887289047241},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8022927045822144},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6603208184242249},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.628106951713562},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6272268295288086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5971039533615112},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.5631053447723389},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4918253421783447},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4599444568157196},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4512563645839691},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2672466039657593},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07103684544563293}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.909055769443512},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8322001695632935},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.8235887289047241},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8022927045822144},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6603208184242249},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.628106951713562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6272268295288086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5971039533615112},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5631053447723389},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4918253421783447},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4599444568157196},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4512563645839691},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2672466039657593},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07103684544563293},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2009.4960587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960587","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.156.8546","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.156.8546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-speech.sri.com/cgi-bin/run-distill?papers/icassp2009-mand-lexicon.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.525.5935","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.525.5935","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.speech.sri.com/people/leixin/papers/LearnDict.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7099999785423279,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310094","display_name":"University of Washington","ror":"https://ror.org/00cvxb145"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W103244930","https://openalex.org/W187680888","https://openalex.org/W238809288","https://openalex.org/W1608381367","https://openalex.org/W2015152466","https://openalex.org/W2097978681","https://openalex.org/W2107176659","https://openalex.org/W2114123841","https://openalex.org/W2149503103","https://openalex.org/W2167423437","https://openalex.org/W6604228424","https://openalex.org/W6636499491","https://openalex.org/W6674334065","https://openalex.org/W6684317040"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","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/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,55,94,104],"data-driven":[3],"framework":[4],"for":[5,27,54],"expanding":[6],"the":[7,22,40,75],"lexicon":[8,19],"to":[9],"improve":[10],"Mandarin":[11,105],"broadcast":[12,106],"news":[13],"and":[14,30,36],"conversation":[15],"speech":[16,107],"recognition.":[17],"The":[18,62],"expansion":[20],"includes":[21],"generation":[23],"of":[24],"pronunciation":[25,52,60,64],"variants":[26,65],"frequent":[28],"words":[29,35,86],"vocabulary":[31],"augmentation":[32],"with":[33],"new":[34,85],"phrases":[37],"derived":[38],"from":[39,57,69],"training":[41],"data.":[42],"To":[43,73],"learn":[44],"multiple":[45],"pronunciations,":[46],"we":[47,78],"first":[48],"generate":[49],"all":[50],"possible":[51],"candidates":[53],"word":[56],"its":[58],"character":[59],"network.":[61],"top":[63],"are":[66],"then":[67],"selected":[68],"forced":[70],"alignment":[71],"statistics.":[72,90],"augment":[74],"acoustic":[76],"vocabulary,":[77],"propose":[79],"an":[80],"efficient":[81],"algorithm":[82],"that":[83,93],"derives":[84],"based":[87],"on":[88,103],"N-gram":[89],"Experiments":[91],"show":[92],"dictionary":[95],"expanded":[96],"in":[97],"this":[98],"manner":[99],"yields":[100],"significant":[101],"improvements":[102],"recognition":[108],"task.":[109]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}