{"id":"https://openalex.org/W2289963167","doi":"https://doi.org/10.1109/asru.2015.7404858","title":"The NAIST ASR system for the 2015 Multi-Genre Broadcast challenge: On combination of deep learning systems using a rank-score function","display_name":"The NAIST ASR system for the 2015 Multi-Genre Broadcast challenge: On combination of deep learning systems using a rank-score function","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2289963167","doi":"https://doi.org/10.1109/asru.2015.7404858","mag":"2289963167"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102847246","display_name":"Quoc Truong","orcid":"https://orcid.org/0000-0003-1472-1370"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Quoc Truong Do","raw_affiliation_strings":["Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015873217","display_name":"Michael Heck","orcid":"https://orcid.org/0000-0001-9841-5025"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Michael Heck","raw_affiliation_strings":["Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000692949","display_name":"Graham Neubig","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":["Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9979000091552734,"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":0.9952999949455261,"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/computer-science","display_name":"Computer science","score":0.819127082824707},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6324262619018555},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6279549598693848},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.580445408821106},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5619593262672424},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5264385938644409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49364838004112244},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4460144340991974},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4269047975540161},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35638630390167236},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.19915342330932617},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07281732559204102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.819127082824707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6324262619018555},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6279549598693848},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.580445408821106},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5619593262672424},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5264385938644409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49364838004112244},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4460144340991974},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4269047975540161},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35638630390167236},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.19915342330932617},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07281732559204102},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2015.7404858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320335839","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W38527073","https://openalex.org/W44815768","https://openalex.org/W264400643","https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W1819316285","https://openalex.org/W1904457459","https://openalex.org/W1993721840","https://openalex.org/W2026369565","https://openalex.org/W2072493763","https://openalex.org/W2097927681","https://openalex.org/W2107638917","https://openalex.org/W2121415728","https://openalex.org/W2134756243","https://openalex.org/W2150769028","https://openalex.org/W2154887136","https://openalex.org/W2171928131","https://openalex.org/W2288371874","https://openalex.org/W2293185259","https://openalex.org/W2405078367","https://openalex.org/W2950186769","https://openalex.org/W4285719527","https://openalex.org/W6601785968","https://openalex.org/W6631362777","https://openalex.org/W6636811518","https://openalex.org/W6682600690"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W164103134","https://openalex.org/W2787352659","https://openalex.org/W1970611213","https://openalex.org/W4206560911","https://openalex.org/W2364370872"],"abstract_inverted_index":{"The":[0,28,127],"Multi-Genre":[1],"Broadcast":[2],"challenge":[3,7],"is":[4],"an":[5],"official":[6],"of":[8,25,36,58,147],"the":[9,23,59,70,81,104,139,144,154],"IEEE":[10],"Automatic":[11],"Speech":[12],"Recognition":[13,88],"and":[14,42,47,53,86,97,108,150],"Understanding":[15],"Workshop.":[16],"This":[17,100],"paper":[18,101],"presents":[19,109],"NAISTs":[20],"contribution":[21],"to":[22,69,121],"premiere":[24],"this":[26],"challenge.":[27],"presented":[29],"speech-to-text":[30],"system":[31,98,105,113,124,131],"for":[32,51,80],"English":[33],"makes":[34],"use":[35],"various":[37],"front-ends":[38],"(e.g.,":[39],"MFCC,":[40],"i-vector":[41,136],"FBANK),":[43],"DNN":[44,128],"acoustic":[45],"models":[46,50],"several":[48],"language":[49],"decoding":[52],"rescoring":[54,96],"(N-gram,":[55],"RNNLM).":[56],"Subsets":[57],"training":[60,72,141],"data":[61],"with":[62,67,138],"varying":[63],"sizes":[64],"were":[65,78],"evaluated":[66],"respect":[68],"overall":[71],"quality.":[73],"Two":[74],"speech":[75],"segmentation":[76],"systems":[77],"developed":[79],"challenge,":[82],"based":[83,112,129],"on":[84,103,133],"DNNs":[85],"GMM-HMMs.":[87],"was":[89],"performed":[90],"in":[91],"three":[92],"stages:":[93],"Decoding,":[94],"lattice":[95],"combination.":[99],"focuses":[102],"combination":[106,125],"experiments":[107],"a":[110,122],"rank-score":[111],"weighting":[114],"approach,":[115],"which":[116],"gave":[117],"better":[118],"performance":[119,146],"compared":[120],"normal":[123],"strategy.":[126],"ASR":[130],"trained":[132],"MFCC":[134],"+":[135],"features":[137],"sMBR":[140,157],"criterion":[142],"gives":[143],"best":[145],"27.8%":[148],"WER,":[149],"thus":[151],"significantly":[152],"outperforms":[153],"baseline":[155],"DNN-HMM":[156],"yielding":[158],"33.7%":[159],"WER.":[160]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}