{"id":"https://openalex.org/W2091719314","doi":"https://doi.org/10.1109/icassp.2010.5495099","title":"Search error risk minimization in Viterbi beam search for speech recognition","display_name":"Search error risk minimization in Viterbi beam search for speech recognition","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2091719314","doi":"https://doi.org/10.1109/icassp.2010.5495099","mag":"2091719314"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 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/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","NTT Communication Science Laboratories, NTT Corporation, 2-4 Hikaridai, Seika-cho, Soraku-gun, Kyoto, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 2-4 Hikaridai, Seika-cho, Soraku-gun, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","NTT Communication Science Laboratories, NTT Corporation, 2-4 Hikaridai, Seika-cho, Soraku-gun, Kyoto, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 2-4 Hikaridai, Seika-cho, Soraku-gun, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018620798","display_name":"Atsushi Nakamura","orcid":"https://orcid.org/0000-0003-0788-2221"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Nakamura","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","NTT Communication Science Laboratories, NTT Corporation, 2-4 Hikaridai, Seika-cho, Soraku-gun, Kyoto, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 2-4 Hikaridai, Seika-cho, Soraku-gun, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087554069"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":1.3935,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85214295,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"i","issue":null,"first_page":"4934","last_page":"4937"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"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":0.9926000237464905,"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/beam-search","display_name":"Beam search","score":0.8375821113586426},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7892059087753296},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7655329704284668},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6244406700134277},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6080866456031799},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6080750823020935},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.602054238319397},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.49030640721321106},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48739153146743774},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.48568233847618103},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.473140150308609},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.46242183446884155},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.4557982087135315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.436617374420166},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4348362684249878},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4227448105812073},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3554189205169678},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14584538340568542}],"concepts":[{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.8375821113586426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7892059087753296},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7655329704284668},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6244406700134277},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6080866456031799},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6080750823020935},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.602054238319397},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.49030640721321106},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48739153146743774},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.48568233847618103},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.473140150308609},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.46242183446884155},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.4557982087135315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.436617374420166},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4348362684249878},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4227448105812073},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3554189205169678},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14584538340568542},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2010.5495099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.433.1139","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.433.1139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.kecl.ntt.co.jp/icl/signal/hori/publications/thori_icassp10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W115173043","https://openalex.org/W1967325250","https://openalex.org/W1977434607","https://openalex.org/W2010624529","https://openalex.org/W2043422002","https://openalex.org/W2092577148","https://openalex.org/W2106669799","https://openalex.org/W2137095888","https://openalex.org/W2138889249","https://openalex.org/W2541794668","https://openalex.org/W6604708085","https://openalex.org/W6644497923","https://openalex.org/W6680244570"],"related_works":["https://openalex.org/W2102309991","https://openalex.org/W1795315578","https://openalex.org/W2373954783","https://openalex.org/W2133857928","https://openalex.org/W2143297499","https://openalex.org/W2535886977","https://openalex.org/W2356694334","https://openalex.org/W2991144886","https://openalex.org/W2790444905","https://openalex.org/W1843778016"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,59,110,115,155,160,167],"method":[4,108,153],"to":[5,29,79,94,136],"optimize":[6],"Viterbi":[7],"beam":[8,27],"search":[9,12,28,74,81,139,164],"based":[10,98],"on":[11,99],"error":[13,82,140],"risk":[14,50,141],"minimization":[15],"in":[16,35,154,166],"large":[17],"vocabulary":[18],"continuous":[19],"speech":[20,24],"recognition":[21,143],"(LVCSR).":[22],"Most":[23],"recognizers":[25],"employ":[26],"speed":[30],"up":[31],"the":[32,45,49,53,66,69,85,120,130,138,146,151],"decoding":[33],"process,":[34],"which":[36],"unpromising":[37],"partial":[38,60],"hypotheses":[39],"are":[40],"pruned":[41],"during":[42],"decoding.":[43],"However,":[44],"pruning":[46,86,111],"step":[47],"involves":[48],"of":[51,129,163],"missing":[52],"best":[54,70],"complete":[55],"hypothesis":[56,61,71,97],"by":[57,83],"discarding":[58],"that":[62,113],"might":[63],"grow":[64],"into":[65],"best.":[67],"Missing":[68],"is":[72,78],"called":[73],"error.":[75],"Our":[76],"purpose":[77],"reduce":[80],"optimizing":[84],"step.":[87,148],"While":[88],"conventional":[89],"methods":[90],"use":[91],"heuristic":[92],"criteria":[93],"prune":[95],"each":[96,125],"its":[100],"score,":[101],"rank,":[102],"and":[103,158],"so":[104],"on,":[105],"our":[106],"proposed":[107],"introduces":[109],"function":[112,131],"makes":[114],"more":[116],"precise":[117],"decision":[118],"using":[119,142],"rich":[121],"features":[122],"extracted":[123],"from":[124],"hypothesis.":[126],"The":[127],"parameters":[128],"can":[132],"be":[133],"estimated":[134],"efficiently":[135],"minimize":[137],"lattices":[144],"at":[145],"training":[147],"We":[149],"implemented":[150],"new":[152],"WFST-based":[156],"decoder":[157],"achieved":[159],"significant":[161],"reduction":[162],"errors":[165],"200K-word":[168],"LVCSR":[169],"task.":[170]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}