{"id":"https://openalex.org/W1576272084","doi":"https://doi.org/10.1109/icassp.2015.7178926","title":"Feature enhancement based on generative-discriminative hybrid approach with gmms and DNNS for noise robust speech recognition","display_name":"Feature enhancement based on generative-discriminative hybrid approach with gmms and DNNS for noise robust speech recognition","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1576272084","doi":"https://doi.org/10.1109/icassp.2015.7178926","mag":"1576272084"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5109368288","display_name":"Masakiyo Fujimoto","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":false,"raw_author_name":"Masakiyo Fujimoto","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Japan","NTT Communication Science Labs, NTT Corp., Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Labs, NTT Corp., Japan#TAB#","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"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":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Japan","NTT Communication Science Labs, NTT Corp., Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Labs, NTT Corp., Japan#TAB#","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5019","last_page":"5023"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/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":0.9994999766349792,"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/discriminative-model","display_name":"Discriminative model","score":0.9229277968406677},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.8065758943557739},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.7378398180007935},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6565755009651184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6119197607040405},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5877785682678223},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5801722407341003},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.48898303508758545},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.42235758900642395},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.0829908549785614}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9229277968406677},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.8065758943557739},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7378398180007935},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6565755009651184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6119197607040405},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5877785682678223},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5801722407341003},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.48898303508758545},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.42235758900642395},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0829908549785614},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W284180566","https://openalex.org/W1973681148","https://openalex.org/W1992012199","https://openalex.org/W1992716054","https://openalex.org/W2008971146","https://openalex.org/W2012174101","https://openalex.org/W2042141988","https://openalex.org/W2045036776","https://openalex.org/W2062164080","https://openalex.org/W2081976287","https://openalex.org/W2090861223","https://openalex.org/W2090958120","https://openalex.org/W2094988970","https://openalex.org/W2116813507","https://openalex.org/W2121973264","https://openalex.org/W2121981798","https://openalex.org/W2122009793","https://openalex.org/W2126597753","https://openalex.org/W2128653836","https://openalex.org/W2134218976","https://openalex.org/W2141411743","https://openalex.org/W2146871184","https://openalex.org/W2147143213","https://openalex.org/W2151484683","https://openalex.org/W2167152389","https://openalex.org/W2168101424","https://openalex.org/W2290318471","https://openalex.org/W2405774341","https://openalex.org/W3147539069","https://openalex.org/W4232307471","https://openalex.org/W6610316872","https://openalex.org/W6653440234","https://openalex.org/W6673244680","https://openalex.org/W6713658392"],"related_works":["https://openalex.org/W2093104230","https://openalex.org/W3014948380","https://openalex.org/W2970216048","https://openalex.org/W3164441579","https://openalex.org/W1576272084","https://openalex.org/W4319999855","https://openalex.org/W2163098067","https://openalex.org/W4235709649","https://openalex.org/W2134102638","https://openalex.org/W1967616013"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,30,65,94],"technique":[4],"that":[5],"combines":[6],"generative":[7,31,124,143],"and":[8,16,55,74],"discriminative":[9,120],"approaches":[10],"with":[11,137],"Gaussian":[12,50],"mixture":[13],"models":[14],"(GMMs)":[15],"deep":[17],"neural":[18],"networks":[19],"(DNNs)":[20],"for":[21,68,108],"model-based":[22,26],"feature":[23,27,72],"enhancement.":[24],"Typical":[25],"enhancement":[28],"employs":[29],"model":[32,144],"approach.":[33,125,145],"The":[34,59,88,112],"enhanced":[35],"features":[36],"are":[37],"obtained":[38,139],"by":[39,48],"using":[40,140],"the":[41,80,104,116,119,123,130,141],"weighted":[42],"sum":[43],"of":[44,61,71,84,91,106,118],"linear":[45],"transformations":[46],"given":[47],"each":[49],"component":[51],"contained":[52],"in":[53],"GMMs":[54],"corresponding":[56],"posterior":[57,62,110],"probabilities.":[58,111],"computation":[60],"probabilities":[63],"is":[64,93],"crucial":[66],"factor":[67],"this":[69,98],"kind":[70],"enhancement,":[73],"can":[75],"also":[76],"be":[77],"formulated":[78],"as":[79],"class":[81],"discrimination":[82,99],"problem":[83],"observed":[85],"noisy":[86],"features.":[87],"prominent":[89],"discriminability":[90],"DNNs":[92,107],"well-known":[95],"solution":[96],"to":[97],"problem.":[100],"Therefore,":[101],"we":[102],"propose":[103],"use":[105],"computing":[109],"proposed":[113,131],"method":[114,132],"incorporates":[115],"benefit":[117],"approach":[121],"into":[122],"For":[126],"AURORA2":[127],"task":[128],"evaluations,":[129],"provided":[133],"noticeable":[134],"improvements":[135],"compared":[136],"results":[138],"conventional":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}