{"id":"https://openalex.org/W2290548146","doi":"https://doi.org/10.1109/apsipa.2015.7415295","title":"Improving denoising auto-encoder based speech enhancement with the speech parameter generation algorithm","display_name":"Improving denoising auto-encoder based speech enhancement with the speech parameter generation algorithm","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2290548146","doi":"https://doi.org/10.1109/apsipa.2015.7415295","mag":"2290548146"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2015.7415295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2015.7415295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","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/A5073046122","display_name":"Syu\u2010Siang Wang","orcid":"https://orcid.org/0000-0002-2652-5521"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Syu-Siang Wang","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101061014","display_name":"Hsin-Te Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Te Hwang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027128278","display_name":"Ying-Hui Lai","orcid":"https://orcid.org/0000-0003-4120-7289"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ying-Hui Lai","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xugang Lu","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015868237","display_name":"Borching Su","orcid":"https://orcid.org/0000-0001-8617-2601"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Borching Su","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5073046122"],"corresponding_institution_ids":["https://openalex.org/I16733864","https://openalex.org/I4210086894"],"apc_list":null,"apc_paid":null,"fwci":2.3285,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.89572304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"365","last_page":"369"},"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":0.9997000098228455,"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":0.9984999895095825,"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":0.7682042717933655},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7518770098686218},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7345468997955322},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5755922198295593},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5638867020606995},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5052276253700256},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4853990972042084},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4613973796367645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4209124445915222},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41026702523231506},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36381134390830994},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3606418967247009},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.342809796333313},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.05997702479362488}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7682042717933655},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7518770098686218},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7345468997955322},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5755922198295593},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5638867020606995},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5052276253700256},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4853990972042084},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4613973796367645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4209124445915222},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41026702523231506},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36381134390830994},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3606418967247009},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.342809796333313},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05997702479362488},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2015.7415295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2015.7415295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1561742478","https://openalex.org/W1935012542","https://openalex.org/W1965555277","https://openalex.org/W1967590528","https://openalex.org/W2013608223","https://openalex.org/W2044893557","https://openalex.org/W2052043556","https://openalex.org/W2052818671","https://openalex.org/W2078528584","https://openalex.org/W2086796102","https://openalex.org/W2092644348","https://openalex.org/W2114826795","https://openalex.org/W2120605154","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2134973740","https://openalex.org/W2141411743","https://openalex.org/W2153894152","https://openalex.org/W2154920538","https://openalex.org/W2158291955","https://openalex.org/W2166844659","https://openalex.org/W2294246205","https://openalex.org/W2394498270","https://openalex.org/W2405774341","https://openalex.org/W2407907561","https://openalex.org/W3147539069","https://openalex.org/W6633652116","https://openalex.org/W6711896204"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W2072884270","https://openalex.org/W4252682934","https://openalex.org/W2089240210"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,6,35,71,88,98,106,137,143,149],"use":[4],"of":[5,77,119,160],"speech":[7,26,40,64,73],"parameter":[8],"generation":[9],"(SPG)":[10],"algorithm,":[11],"which":[12,152],"has":[13],"been":[14],"successfully":[15],"adopted":[16],"in":[17,65,126,158,164],"deep":[18,36],"neural":[19],"network":[20],"(DNN)-based":[21],"voice":[22],"conversion":[23],"(VC)":[24],"and":[25,130,148,168],"synthesis":[27],"(SS),":[28],"for":[29],"incorporating":[30],"temporal":[31,120],"information":[32,121],"to":[33,87,104,111],"improve":[34],"denoising":[37],"auto-encoder":[38],"(DDAE)-based":[39],"enhancement.":[41],"In":[42],"our":[43],"previous":[44],"studies,":[45],"we":[46],"have":[47],"confirmed":[48],"that":[49,136],"DDAE":[50,62,107],"could":[51],"effectively":[52],"suppress":[53],"noise":[54,57,166],"components":[55],"from":[56],"corrupted":[58],"speech.":[59],"However,":[60],"because":[61],"converts":[63],"a":[66,102,114],"frame":[67,69],"by":[68],"manner,":[70],"enhanced":[72],"shows":[74],"some":[75],"level":[76],"discontinuity":[78],"even":[79],"though":[80],"context":[81,131,140,154],"features":[82,141,147,155],"are":[83,124],"used":[84],"as":[85,101],"input":[86],"DDAE.":[89],"To":[90],"handle":[91],"this":[92,94,127],"issue,":[93],"study":[95],"proposes":[96],"using":[97],"SPG":[99,123,138,144],"algorithm":[100],"post-processor":[103],"transform":[105],"processed":[108],"feature":[109],"sequence":[110],"one":[112],"with":[113,122,139,145],"smoothed":[115],"trajectory.":[116],"Two":[117],"types":[118,167],"investigated":[125],"study:":[128],"static-dynamic":[129,146],"features.":[132],"Experimental":[133],"results":[134],"show":[135],"outperforms":[142],"baseline":[150],"system,":[151],"considers":[153],"without":[156],"SPG,":[157],"terms":[159],"standardized":[161],"objective":[162],"tests":[163],"different":[165],"SNRs.":[169]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
