{"id":"https://openalex.org/W1778816975","doi":"https://doi.org/10.21437/interspeech.2014-441","title":"DNN-based stochastic postfilter for HMM-based speech synthesis","display_name":"DNN-based stochastic postfilter for HMM-based speech synthesis","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W1778816975","doi":"https://doi.org/10.21437/interspeech.2014-441","mag":"1778816975"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-441","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/24ab5cc8-f327-4bcc-91ce-c74c742e0010","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101593418","display_name":"Ling-Hui Chen","orcid":"https://orcid.org/0009-0009-4247-4128"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling-Hui Chen","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000571465","display_name":"Tuomo Raitio","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuomo Raitio","raw_affiliation_strings":["Department of Signal Processing and Acoustics Aalto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics Aalto University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019012876","display_name":"Cassia Valentini-Botinhao","orcid":"https://orcid.org/0000-0002-3486-8620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cassia Valentini-Botinhao","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9287,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.95158559,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1954","last_page":"1958"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9966999888420105,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9725000262260437,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.782516360282898},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7422803640365601},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6934463977813721},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5090956091880798},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5021803379058838},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.46080446243286133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4482106864452362},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4380864202976227},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42122119665145874},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40273985266685486},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07424280047416687}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.782516360282898},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7422803640365601},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6934463977813721},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5090956091880798},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5021803379058838},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.46080446243286133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4482106864452362},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4380864202976227},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42122119665145874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40273985266685486},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07424280047416687},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2014-441","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.720.3444","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.720.3444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2014/postfilter_IS14.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/24ab5cc8-f327-4bcc-91ce-c74c742e0010","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/dnnbased-stochastic-postfilter-for-hmmbased-speech-synthesis(24ab5cc8-f327-4bcc-91ce-c74c742e0010).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:openaire/24ab5cc8-f327-4bcc-91ce-c74c742e0010","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/24ab5cc8-f327-4bcc-91ce-c74c742e0010","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Chen, L-H, Raitio, T, Valentini-Botinhao, C, Yamagishi, J & Ling, Z-H 2014, DNN-based stochastic postfilter for HMM-based speech synthesis. in Interspeech 2014. International Speech Communication Association, Singapore, pp. 1954-1958. < http://www.isca-speech.org/archive/interspeech_2014/i14_1954.html >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/24ab5cc8-f327-4bcc-91ce-c74c742e0010","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/24ab5cc8-f327-4bcc-91ce-c74c742e0010","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Chen, L-H, Raitio, T, Valentini-Botinhao, C, Yamagishi, J & Ling, Z-H 2014, DNN-based stochastic postfilter for HMM-based speech synthesis. in Interspeech 2014. International Speech Communication Association, Singapore, pp. 1954-1958. < http://www.isca-speech.org/archive/interspeech_2014/i14_1954.html >","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W157817982","https://openalex.org/W1813659000","https://openalex.org/W1987992317","https://openalex.org/W2000513720","https://openalex.org/W2010833326","https://openalex.org/W2020024436","https://openalex.org/W2049686551","https://openalex.org/W2093231248","https://openalex.org/W2093450784","https://openalex.org/W2095425517","https://openalex.org/W2100495367","https://openalex.org/W2108674328","https://openalex.org/W2116064496","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2129142580","https://openalex.org/W2164700406","https://openalex.org/W2407907561"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W3145575561","https://openalex.org/W2995886640","https://openalex.org/W2038801705","https://openalex.org/W2688184458","https://openalex.org/W2904846757"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"propose":[4],"a":[5],"deep":[6],"neural":[7],"network":[8],"to":[9,26,70],"model":[10],"the":[11,15,28,39,58,63,71],"conditional":[12],"probability":[13],"of":[14,66],"spectral":[16,29],"differences":[17],"between":[18],"nat-ural":[19],"and":[20,50],"synthetic":[21,67],"speech.":[22],"This":[23],"allows":[24],"us":[25],"reconstruct":[27],"fine":[30],"structures":[31],"in":[32],"speech":[33,68,77],"generated":[34],"by":[35],"HMMs.":[36],"We":[37],"com-pared":[38],"new":[40],"stochastic":[41],"data-driven":[42],"postfilter":[43],"with":[44],"global":[45],"vari-ance":[46],"based":[47],"parameter":[48],"generation":[49],"modulation":[51,80],"spectrum":[52],"en-hancement.":[53],"Our":[54],"results":[55],"confirm":[56],"that":[57],"proposed":[59],"method":[60],"sig-nificantly":[61],"improves":[62],"segmental":[64,83],"quality":[65,84],"compared":[69],"conventional":[72],"methods.":[73],"Index":[74],"Terms:":[75],"HMM,":[76],"synthesis,":[78],"DNN,":[79],"spectrum,":[81],"postfilter,":[82]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}