{"id":"https://openalex.org/W3001745422","doi":"https://doi.org/10.1145/3372806.3372819","title":"Minimum Classification Error Training with Speech Synthesis-Based Regularization for Speech Recognition","display_name":"Minimum Classification Error Training with Speech Synthesis-Based Regularization for Speech Recognition","publication_year":2019,"publication_date":"2019-11-27","ids":{"openalex":"https://openalex.org/W3001745422","doi":"https://doi.org/10.1145/3372806.3372819","mag":"3001745422"},"language":"en","primary_location":{"id":"doi:10.1145/3372806.3372819","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372806.3372819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 2nd International Conference on Signal Processing and Machine Learning","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/A5035500163","display_name":"Naoto Umezaki","orcid":null},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoto Umezaki","raw_affiliation_strings":["Graduate School of Science and Engineering, Doshisha University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Doshisha University, Kyoto, Japan","institution_ids":["https://openalex.org/I133984924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062891759","display_name":"Takumi Okubo","orcid":"https://orcid.org/0009-0009-6627-8383"},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takumi Okubo","raw_affiliation_strings":["Graduate School of Science and Engineering, Doshisha University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Doshisha University, Kyoto, Japan","institution_ids":["https://openalex.org/I133984924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101136257","display_name":"Hideyuki Watanabe","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideyuki Watanabe","raw_affiliation_strings":["Advanced Telecommunications Research Institute International, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Telecommunications Research Institute International, Kyoto, Japan","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027443847","display_name":"Shigeru Katagiri","orcid":"https://orcid.org/0000-0003-4738-5385"},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeru Katagiri","raw_affiliation_strings":["Graduate School of Science and Engineering, Doshisha University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Doshisha University, Kyoto, Japan","institution_ids":["https://openalex.org/I133984924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024098357","display_name":"Miho Ohsaki","orcid":"https://orcid.org/0000-0002-6766-2928"},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Miho Ohsaki","raw_affiliation_strings":["Graduate School of Science and Engineering, Doshisha University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Doshisha University, Kyoto, Japan","institution_ids":["https://openalex.org/I133984924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"62","last_page":"72"},"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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/speech-recognition","display_name":"Speech recognition","score":0.7895526885986328},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.727185845375061},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6280487775802612},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.49866819381713867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44699159264564514},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36229273676872253},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3320434093475342}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7895526885986328},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.727185845375061},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6280487775802612},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.49866819381713867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44699159264564514},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36229273676872253},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3320434093475342},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3372806.3372819","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372806.3372819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 2nd International Conference on Signal Processing and Machine Learning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G1356720127","display_name":"Construction of Class Boundary Evaluation Criterion in Pattern Recognition","funder_award_id":"18H03266","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1770825568","https://openalex.org/W1981258758","https://openalex.org/W1983989471","https://openalex.org/W2002011878","https://openalex.org/W2063541597","https://openalex.org/W2111284386","https://openalex.org/W2112081648","https://openalex.org/W2135346934","https://openalex.org/W2142635246","https://openalex.org/W2148603752","https://openalex.org/W2151626637","https://openalex.org/W2944529878","https://openalex.org/W2990597923","https://openalex.org/W3106889297","https://openalex.org/W3152218910","https://openalex.org/W6629510986"],"related_works":["https://openalex.org/W2611614995","https://openalex.org/W2368651715","https://openalex.org/W2789919619","https://openalex.org/W1552159754","https://openalex.org/W2148757832","https://openalex.org/W2293457016","https://openalex.org/W2131420137","https://openalex.org/W3169305685","https://openalex.org/W2033914206","https://openalex.org/W3107474891"],"abstract_inverted_index":{"To":[0,44],"increase":[1],"the":[2,13,37,78,83,116,123,175,183,186,194,200,203,211,217],"utility":[3],"of":[4,15,41,154,177,185,202],"Regularization,":[5],"which":[6],"is":[7,139,207],"a":[8,25,32,52,67,73,86,97,108,160,165],"common":[9],"framework":[10],"for":[11,19,105],"avoiding":[12],"underestimation":[14],"ideal":[16],"Bayes":[17,137,155,204],"error,":[18],"speech":[20,38,53,79,133,188,212],"recognizer":[21,54],"training,":[22],"we":[23,49,181],"propose":[24],"new":[26,47,98],"classifier":[27,42],"training":[28,87,103,125,162,166],"concept":[29],"that":[30,35,55,76,147,199],"incorporates":[31],"regularization":[33,74,119],"term":[34,75],"represents":[36,77],"synthesis":[39,80,213],"ability":[40,81,214],"parameters.":[43],"implement":[45],"our":[46,148],"concept,":[48],"first":[50],"introduce":[51],"embeds":[56],"Line":[57],"Spectral":[58],"Pairs-Conjugate":[59],"Structure-Algebraic":[60],"Code":[61],"Excited":[62],"Linear":[63],"Prediction":[64],"(LSP-CS-ACELP)":[65],"in":[66,127,216],"Multi-Prototype":[68],"State-Transition-Model":[69],"(MP-STM)":[70],"classifier,":[71],"define":[72],"by":[82,210],"distance":[84],"between":[85],"sample":[88,178],"and":[89,95,115,131,145,197],"its":[90],"nearest":[91],"MP-STM":[92],"word":[93],"model,":[94],"formalize":[96],"Minimum":[99],"Classification":[100],"Error":[101],"(MCE)":[102],"method":[104,126,149],"jointly":[106],"minimizing":[107],"conventional":[109],"smooth":[110],"classification":[111],"error":[112,138,156,205],"count":[113],"loss":[114],"newly":[117],"defined":[118],"term.":[120],"We":[121],"evaluated":[122],"proposed":[124],"an":[128,152],"isolated-word,":[129],"closed-vocabulary,":[130],"speaker-independent":[132],"recognition":[134],"task":[135],"whose":[136],"estimated":[140],"to":[141],"be":[142],"about":[143],"20%":[144],"found":[146,198],"successfully":[150],"produced":[151],"estimate":[153],"(about":[157],"18.4%)":[158],"with":[159],"single":[161],"run":[163],"over":[164],"dataset":[167],"without":[168],"such":[169],"data":[170],"resampling":[171],"as":[172],"Cross-Validation":[173],"or":[174],"assumptions":[176],"distribution.":[179],"Moreover,":[180],"investigated":[182],"quality":[184,201],"synthesized":[187],"using":[189],"LSP":[190],"parameters":[191],"derived":[192],"from":[193],"trained":[195],"prototypes":[196],"estimation":[206],"clearly":[208],"supported":[209],"preserved":[215],"training.":[218]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}