{"id":"https://openalex.org/W2095547148","doi":"https://doi.org/10.1109/icassp.2013.6639147","title":"Large vocabulary continuous speech recognition based on WFST structured classifiers and deep bottleneck features","display_name":"Large vocabulary continuous speech recognition based on WFST structured classifiers and deep bottleneck features","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2095547148","doi":"https://doi.org/10.1109/icassp.2013.6639147","mag":"2095547148"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 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/A5102252420","display_name":"Yotaro Kubo","orcid":null},"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":"Yotaro Kubo","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","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":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan","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, Kyoto, Japan","NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102252420"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":3.3663,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.92781125,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"7629","last_page":"7633"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9973999857902527,"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/T10860","display_name":"Speech and Audio Processing","score":0.9962000250816345,"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/computer-science","display_name":"Computer science","score":0.7851969599723816},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6227441430091858},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5955120921134949},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5235345363616943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5223211646080017},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5208899974822998},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5186138153076172},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5162139534950256},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.4921392798423767},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47420409321784973},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46666067838668823},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42020294070243835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7851969599723816},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6227441430091858},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5955120921134949},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5235345363616943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5223211646080017},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5208899974822998},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5186138153076172},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5162139534950256},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.4921392798423767},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47420409321784973},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46666067838668823},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42020294070243835},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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.2013.6639147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 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":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1934041838","https://openalex.org/W1984196678","https://openalex.org/W1993882792","https://openalex.org/W2036912417","https://openalex.org/W2079674300","https://openalex.org/W2082890803","https://openalex.org/W2097428361","https://openalex.org/W2125234026","https://openalex.org/W2131033001","https://openalex.org/W2138889249","https://openalex.org/W2144792281","https://openalex.org/W2150907703","https://openalex.org/W2154198224","https://openalex.org/W2156615793","https://openalex.org/W2167270514","https://openalex.org/W2169384404","https://openalex.org/W2394932179","https://openalex.org/W2398758402","https://openalex.org/W2399086392","https://openalex.org/W2403195671","https://openalex.org/W2951282416","https://openalex.org/W3149335959","https://openalex.org/W3161062409","https://openalex.org/W6674634876","https://openalex.org/W6681232967","https://openalex.org/W6683422774","https://openalex.org/W6684930139","https://openalex.org/W6712593814"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1001352512","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138"],"abstract_inverted_index":{"Recently,":[0],"structured":[1,50,124],"classification":[2,125],"approaches":[3],"have":[4],"been":[5,86,94],"considered":[6,165],"important":[7],"with":[8,126,155,201],"a":[9,34,54,58,121,149,202],"view":[10],"to":[11,184],"achieving":[12],"unified":[13,27],"modeling":[14],"of":[15,21,46,69,81,99,145],"the":[16,39,42,47,65,70,76,79,97,142,146,156,168,171,174,179,186],"acoustic":[17,136,204],"and":[18,44,67,91],"linguistic":[19],"aspects":[20],"speech":[22,109],"recognizers.":[23],"With":[24],"these":[25],"approaches,":[26],"representation":[28,176],"is":[29,72,153],"achieved":[30,192],"by":[31,88],"directly":[32],"optimizing":[33],"score":[35,59],"function":[36,56],"that":[37,96,111,139],"measures":[38],"correspondence":[40],"between":[41],"input":[43,66,169],"output":[45,68,175],"system.":[48],"Since":[49,160],"classifiers":[51],"typically":[52],"employ":[53],"linear":[55],"as":[57],"function,":[60],"extracting":[61],"expressive":[62],"features":[63,110,162],"from":[64],"system":[71],"very":[73],"important.":[74],"On":[75],"other":[77],"hand,":[78],"effectiveness":[80],"deep":[82,103],"neural":[83,104],"networks":[84,105],"has":[85,93],"verified":[87],"several":[89],"experiments,":[90],"it":[92],"suggested":[95],"outputs":[98],"hidden":[100],"layers":[101],"in":[102,148,167,173],"(DNNs)":[106],"are":[107,182],"essential":[108],"purely":[112],"express":[113],"phonetic":[114],"information.":[115],"In":[116],"this":[117],"paper,":[118],"we":[119],"propose":[120],"method":[122,131,191],"for":[123],"DNN":[127],"features.":[128,188],"The":[129,189],"proposed":[130,190],"expands":[132],"conventional":[133],"DNN-":[134],"based":[135,177,206],"models":[137],"so":[138],"they":[140],"optimizes":[141],"weight":[143],"terms":[144],"arcs":[147,181],"decoding":[150],"WFST,":[151],"which":[152],"constructed":[154],"on-the-fly":[157],"composition":[158],"method.":[159],"DNN-based":[161,187],"can":[163],"be":[164],"enhancements":[166,172],"representation,":[170],"on":[178,207],"WFST":[180],"expected":[183],"complement":[185],"an":[193],"8":[194],"%":[195],"relative":[196],"error":[197],"reduction":[198],"even":[199],"compared":[200],"strong":[203],"model":[205],"DNNs.":[208]},"counts_by_year":[{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}