{"id":"https://openalex.org/W2673599284","doi":"https://doi.org/10.1109/icassp.2017.7952156","title":"Deep mixture density network for statistical model-based feature enhancement","display_name":"Deep mixture density network for statistical model-based feature enhancement","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2673599284","doi":"https://doi.org/10.1109/icassp.2017.7952156","mag":"2673599284"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"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":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"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":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"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":"Atsunori Ogawa","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101768343","display_name":"Takuya Higuchi","orcid":"https://orcid.org/0000-0002-0361-7132"},"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":"Takuya Higuchi","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation","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":"251","last_page":"255"},"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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":0.9976000189781189,"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/feature","display_name":"Feature (linguistics)","score":0.7333558201789856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6206480860710144},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5622222423553467},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5453065037727356},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5398383140563965},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5187128186225891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4965868592262268},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.47017544507980347},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4163627624511719},{"id":"https://openalex.org/keywords/mixture-distribution","display_name":"Mixture distribution","score":0.4118432104587555},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36600667238235474},{"id":"https://openalex.org/keywords/probability-density-function","display_name":"Probability density function","score":0.2375825047492981},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2061755657196045},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.12326273322105408},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08815246820449829}],"concepts":[{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7333558201789856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6206480860710144},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5622222423553467},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5453065037727356},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5398383140563965},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5187128186225891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4965868592262268},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.47017544507980347},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4163627624511719},{"id":"https://openalex.org/C56672385","wikidata":"https://www.wikidata.org/wiki/Q17157111","display_name":"Mixture distribution","level":3,"score":0.4118432104587555},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36600667238235474},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.2375825047492981},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2061755657196045},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.12326273322105408},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08815246820449829},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/icassp.2017.7952156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W102482883","https://openalex.org/W595249637","https://openalex.org/W1482149378","https://openalex.org/W1578856370","https://openalex.org/W1579853615","https://openalex.org/W2010023285","https://openalex.org/W2013608223","https://openalex.org/W2042071805","https://openalex.org/W2078528584","https://openalex.org/W2124149378","https://openalex.org/W2126597753","https://openalex.org/W2149648698","https://openalex.org/W2158291955","https://openalex.org/W2160306971","https://openalex.org/W2290318471","https://openalex.org/W2398042854","https://openalex.org/W2486913545","https://openalex.org/W4206633762","https://openalex.org/W6682181234","https://openalex.org/W6683202405"],"related_works":["https://openalex.org/W2198732287","https://openalex.org/W4287816759","https://openalex.org/W2044981176","https://openalex.org/W2598185551","https://openalex.org/W2017090935","https://openalex.org/W2116212858","https://openalex.org/W2032556230","https://openalex.org/W2372918136","https://openalex.org/W3119669586","https://openalex.org/W1578916557"],"abstract_inverted_index":{"We":[0,211],"propose":[1],"a":[2,34,39,111,118,127,139,175,220],"novel":[3],"framework":[4,23,182,195],"designed":[5],"to":[6,25,30,67,126,157,173],"extend":[7],"conventional":[8,19,88,221],"deep":[9],"neural":[10,119],"network":[11,114,120],"(DNN)-based":[12],"feature":[13,21,64,101,125,149,186,223],"enhancement":[14,22,65,224],"approaches.":[15],"In":[16,188],"general,":[17],"the":[18,49,52,62,74,84,87,97,136,144,160,163,170,181,193,197,208,215],"DNN-based":[20,100,222],"aims":[24],"map":[26],"input":[27,50,82,124],"noisy":[28],"observation":[29],"clean":[31,147,177],"speech":[32,148,178],"or":[33],"binary/":[35],"soft":[36],"mask":[37],"in":[38,86,162,180],"deterministic":[40],"way,":[41],"assuming":[42],"that":[43,61,121,214],"there":[44],"is":[45,90,117],"one-to-one":[46],"mapping":[47,75],"between":[48],"and":[51,94,196,202],"output":[53],"without":[54],"any":[55],"uncertainty.":[56],"However,":[57],"when":[58],"we":[59,153,167,199],"consider":[60,159],"general":[63],"problem":[66,72],"be":[68,77],"an":[69,81,123],"ill-posed":[70],"inverse":[71],"where":[73],"cannot":[76],"uniquely":[78],"determined":[79],"given":[80],"signal,":[83],"assumption":[85],"approaches":[89],"not":[91],"theoretically":[92],"correct":[93],"potentially":[95],"limits":[96],"performance":[98],"of":[99,129,138,146,183],"enhancement.":[102,187],"To":[103],"overcome":[104],"this":[105,107,189],"problem,":[106],"paper":[108],"proposes":[109],"utilizing":[110],"mixture":[112,131],"density":[113],"(MDN),":[115],"which":[116],"maps":[122],"set":[128],"Gaussian":[130],"model":[132],"(GMM)":[133],"parameters":[134],"representing":[135],"distribution":[137,145],"target":[140],"variable.":[141],"By":[142],"estimating":[143],"based":[150],"on":[151],"MDN,":[152,198],"are":[154],"now":[155],"able":[156],"explicitly":[158],"uncertainty":[161,209],"parameter":[164],"estimation.":[165],"Then,":[166],"further":[168],"utilizes":[169],"estimated":[171],"GMM":[172],"obtain":[174],"refined":[176],"estimate":[179],"statistical":[184],"model-based":[185],"paper,":[190],"after":[191],"detailing":[192],"proposed":[194,216],"show":[200,213],"mathematically":[201],"experimentally":[203],"how":[204],"MDN":[205],"appropriately":[206],"models":[207],"information.":[210],"also":[212],"method":[217],"can":[218],"outperform":[219],"method.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}