{"id":"https://openalex.org/W2775589536","doi":"https://doi.org/10.1109/mlsp.2017.8168174","title":"Speech recognition features based on deep latent Gaussian models","display_name":"Speech recognition features based on deep latent Gaussian models","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2775589536","doi":"https://doi.org/10.1109/mlsp.2017.8168174","mag":"2775589536"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2017.8168174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2017.8168174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5038296765","display_name":"Andros Tjandra","orcid":"https://orcid.org/0000-0003-1246-5908"},"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":true,"raw_author_name":"Andros Tjandra","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, 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":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, 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":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038296765"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.195,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64222309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"18","issue":null,"first_page":"1","last_page":"6"},"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9988999962806702,"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":0.7213476896286011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6547431945800781},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.6542510390281677},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.6054823994636536},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5972332954406738},{"id":"https://openalex.org/keywords/graphical-model","display_name":"Graphical model","score":0.5508874654769897},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5424959659576416},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5288456678390503},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5188645124435425},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49666649103164673},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.49419453740119934},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.488757848739624},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.48321473598480225},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.45766499638557434},{"id":"https://openalex.org/keywords/deep-belief-network","display_name":"Deep belief network","score":0.44541317224502563},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43883803486824036},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.41614794731140137},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.34513115882873535},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.3344610035419464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7213476896286011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6547431945800781},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.6542510390281677},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.6054823994636536},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5972332954406738},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.5508874654769897},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5424959659576416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5288456678390503},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5188645124435425},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49666649103164673},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.49419453740119934},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.488757848739624},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.48321473598480225},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.45766499638557434},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.44541317224502563},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43883803486824036},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.41614794731140137},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.34513115882873535},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3344610035419464},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp.2017.8168174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2017.8168174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4000000059604645}],"awards":[],"funders":[{"id":"https://openalex.org/F4320333293","display_name":"South Dakota Agricultural Experiment Station","ror":null},{"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":30,"referenced_works":["https://openalex.org/W189596042","https://openalex.org/W1524333225","https://openalex.org/W1550985492","https://openalex.org/W1661756259","https://openalex.org/W1691728462","https://openalex.org/W1903355235","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W1964812476","https://openalex.org/W1984541135","https://openalex.org/W1990470142","https://openalex.org/W1993882792","https://openalex.org/W1995997122","https://openalex.org/W2054658115","https://openalex.org/W2058641082","https://openalex.org/W2062227835","https://openalex.org/W2095705004","https://openalex.org/W2108501770","https://openalex.org/W2108677974","https://openalex.org/W2123237149","https://openalex.org/W2136922672","https://openalex.org/W2160815625","https://openalex.org/W2163922914","https://openalex.org/W2172097686","https://openalex.org/W2291027405","https://openalex.org/W6607775107","https://openalex.org/W6631362777","https://openalex.org/W6636969168","https://openalex.org/W6674330103","https://openalex.org/W6676315081"],"related_works":["https://openalex.org/W4290803287","https://openalex.org/W2106257677","https://openalex.org/W2964321162","https://openalex.org/W4322716735","https://openalex.org/W2887732792","https://openalex.org/W2616125534","https://openalex.org/W2963987720","https://openalex.org/W3022187094","https://openalex.org/W2146310005","https://openalex.org/W2963790827"],"abstract_inverted_index":{"This":[0],"paper":[1],"constructs":[2],"speech":[3],"features":[4,56,73,89,101],"based":[5,47],"on":[6,48],"a":[7,11,35,58,91],"generative":[8],"model":[9,15],"using":[10,20,102],"deep":[12,59],"latent":[13,45],"Gaussian":[14,49],"(DLGM),":[16],"which":[17,51,113],"is":[18,52],"trained":[19,41],"stochastic":[21],"gradient":[22],"variational":[23],"Bayes":[24],"(SGVB)":[25],"algorithm":[26],"and":[27,32,71,77,87,117],"performs":[28],"efficient":[29],"approximate":[30],"inference":[31],"learning":[33],"with":[34,70],"directed":[36],"probabilistic":[37],"graphical":[38],"model.":[39,64],"The":[40],"DLGM":[42,76,103],"then":[43],"generate":[44],"variables":[46],"distribution,":[50],"used":[53],"as":[54],"new":[55],"for":[57],"neural":[60],"network":[61],"(DNN)":[62],"acoustic":[63,111],"Here":[65],"we":[66],"compare":[67],"our":[68],"results":[69,96],"without":[72],"transformed":[74],"by":[75],"also":[78],"observe":[79],"the":[80,85,99,105,109,115,121],"benefits":[81],"of":[82],"combining":[83],"both":[84],"proposed":[86,100,116],"original":[88,118],"into":[90],"single":[92],"DNN.":[93],"Our":[94],"experimental":[95],"show":[97],"that":[98],"improved":[104],"ASR":[106],"performance.":[107],"Furthermore,":[108],"DNN":[110],"model,":[112],"combined":[114],"features,":[119],"gave":[120],"best":[122],"performances.":[123]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}