{"id":"https://openalex.org/W2914037612","doi":"https://doi.org/10.1109/icassp.2019.8683714","title":"DNN-based Speaker-adaptive Postfiltering with Limited Adaptation Data for Statistical Speech Synthesis Systems","display_name":"DNN-based Speaker-adaptive Postfiltering with Limited Adaptation Data for Statistical Speech Synthesis Systems","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2914037612","doi":"https://doi.org/10.1109/icassp.2019.8683714","mag":"2914037612"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5009478177","display_name":"Mira\u00e7 G\u00f6ksu \u00d6zt\u00fcrk","orcid":null},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Mira\u00e7 G\u00f6ksu \u00d6zt\u00fcrk","raw_affiliation_strings":["Bo&#x011F;azi&#x00E7;i University","Bo\u011fazi\u00e7i University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bo&#x011F;azi&#x00E7;i University","institution_ids":[]},{"raw_affiliation_string":"Bo\u011fazi\u00e7i University","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034761131","display_name":"Okan Ulusoy","orcid":null},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Okan Ulusoy","raw_affiliation_strings":["Bo&#x011F;azi&#x00E7;i University","Bo\u011fazi\u00e7i University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bo&#x011F;azi&#x00E7;i University","institution_ids":[]},{"raw_affiliation_string":"Bo\u011fazi\u00e7i University","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016845689","display_name":"Cenk Demiro\u011flu","orcid":"https://orcid.org/0000-0002-6160-3169"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cenk Demiroglu","raw_affiliation_strings":["&#x00D6;zye&#x011F;in University","Electrical & Electronics Engineering Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"&#x00D6;zye&#x011F;in University","institution_ids":[]},{"raw_affiliation_string":"Electrical & Electronics Engineering Istanbul, Turkey","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4374,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64661334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7030","last_page":"7034"},"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":0.9968000054359436,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9926000237464905,"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/computer-science","display_name":"Computer science","score":0.8129630088806152},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.693030595779419},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6153557896614075},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5968887209892273},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5633467435836792},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5242971777915955},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5147593021392822},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.442616730928421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8129630088806152},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.693030595779419},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6153557896614075},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5968887209892273},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5633467435836792},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5242971777915955},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5147593021392822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.442616730928421},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8683714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:eresearch.ozyegin.edu.tr:10679/6846","is_oa":false,"landing_page_url":"http://hdl.handle.net/10679/6846","pdf_url":null,"source":{"id":"https://openalex.org/S4306400232","display_name":"ECS Journal of Solid State Science and Technology (The Electrochemical Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2802273670","host_organization_name":"Electrochemical Society","host_organization_lineage":["https://openalex.org/I2802273670"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1990505856","https://openalex.org/W2049036695","https://openalex.org/W2102003408","https://openalex.org/W2134973740","https://openalex.org/W2150769028","https://openalex.org/W2154920538","https://openalex.org/W2295570191","https://openalex.org/W2296704011","https://openalex.org/W2400679416","https://openalex.org/W2519091744","https://openalex.org/W2666408839","https://openalex.org/W2769810959","https://openalex.org/W2788357188","https://openalex.org/W2789740382","https://openalex.org/W2888922217","https://openalex.org/W2949382160","https://openalex.org/W2963192573","https://openalex.org/W2963782041","https://openalex.org/W2963796886","https://openalex.org/W2963830550","https://openalex.org/W2964121744","https://openalex.org/W4294226187","https://openalex.org/W4294619240","https://openalex.org/W6631190155","https://openalex.org/W6697285287","https://openalex.org/W6697463866","https://openalex.org/W6748588790"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W2050451745","https://openalex.org/W2378903222"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"have":[4,22],"been":[5,24],"successfully":[6],"deployed":[7],"for":[8,37,70,100],"acoustic":[9],"modelling":[10],"in":[11,34],"statistical":[12],"parametric":[13],"speech":[14],"synthesis":[15],"(SPSS)":[16],"systems.":[17],"Moreover,":[18],"DNN-based":[19,46,71],"postfilters":[20,29,47,72,90],"(PF)":[21],"also":[23],"shown":[25],"to":[26,60,76],"outperform":[27],"conventional":[28],"that":[30,54,73,105],"are":[31,48],"widely":[32],"used":[33],"SPSS":[35,55],"systems":[36,56],"increasing":[38],"the":[39,106,117],"quality":[40],"of":[41],"synthesized":[42],"speech.":[43],"However,":[44],"existing":[45],"trained":[49],"with":[50,79,92,111],"speaker-dependent":[51],"databases.":[52],"Given":[53],"can":[57,74],"rapidly":[58],"adapt":[59,75],"new":[61,77],"speakers":[62,78],"from":[63],"generic":[64],"models,":[65],"there":[66],"is":[67],"a":[68],"need":[69],"minimal":[80],"adaptation":[81],"data.":[82],"Here,":[83],"we":[84],"compare":[85],"DNN-,":[86],"RNN-,":[87],"and":[88,96,113],"CNN-based":[89],"together":[91,110],"adversarial":[93],"(GAN)":[94],"training":[95],"cluster-based":[97],"initialization":[98],"(CI)":[99],"rapid":[101],"adaptation.":[102],"Results":[103],"indicate":[104],"feedforward":[107],"(FF)":[108],"DNN,":[109],"GAN":[112],"CI,":[114],"significantly":[115],"outperforms":[116],"other":[118],"recently":[119],"proposed":[120],"postfilters.":[121]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
