{"id":"https://openalex.org/W1543299179","doi":"https://doi.org/10.21437/interspeech.2015-268","title":"Towards minimum perceptual error training for DNN-based speech synthesis","display_name":"Towards minimum perceptual error training for DNN-based speech synthesis","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W1543299179","doi":"https://doi.org/10.21437/interspeech.2015-268","mag":"1543299179"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-268","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.pure.ed.ac.uk/ws/files/19844220/master.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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/A5102765381","display_name":"Zhizheng Wu","orcid":"https://orcid.org/0009-0001-1192-9857"},"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":"Zhizheng Wu","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"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":"Simon King","raw_affiliation_strings":["School of Philosophy Psychology and Language Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Philosophy Psychology and Language Sciences","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"869","last_page":"873"},"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":0.9998999834060669,"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":0.9988999962806702,"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/speech-recognition","display_name":"Speech recognition","score":0.8120729923248291},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.7534027099609375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7392820119857788},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5252717733383179},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.49371251463890076},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.48649710416793823},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46846291422843933},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4657614529132843},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4632839560508728},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4581098258495331},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45204997062683105},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43872955441474915},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.433474600315094},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4192074239253998},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4165884852409363},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39861583709716797},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.19255095720291138},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18054139614105225},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.10511854290962219},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0693904459476471}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8120729923248291},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.7534027099609375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7392820119857788},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5252717733383179},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.49371251463890076},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.48649710416793823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46846291422843933},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4657614529132843},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4632839560508728},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4581098258495331},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45204997062683105},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43872955441474915},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.433474600315094},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4192074239253998},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4165884852409363},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39861583709716797},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.19255095720291138},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18054139614105225},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10511854290962219},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0693904459476471},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2015-268","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/6b6d3ab3-d621-404e-a75a-8a2a8761a08b","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/6b6d3ab3-d621-404e-a75a-8a2a8761a08b","pdf_url":"https://www.pure.ed.ac.uk/ws/files/19844220/master.pdf","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:CiteSeerX.psu:10.1.1.715.6291","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.715.6291","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/2015/dnncost_IS15.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/6b6d3ab3-d621-404e-a75a-8a2a8761a08b","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/6b6d3ab3-d621-404e-a75a-8a2a8761a08b","pdf_url":"https://www.pure.ed.ac.uk/ws/files/19844220/master.pdf","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":""},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6700000166893005}],"awards":[{"id":"https://openalex.org/G3790594077","display_name":"Natural Speech Technology","funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1543299179.pdf","grobid_xml":"https://content.openalex.org/works/W1543299179.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1499332833","https://openalex.org/W1545406001","https://openalex.org/W1588479472","https://openalex.org/W1778816975","https://openalex.org/W1963637322","https://openalex.org/W1979449467","https://openalex.org/W1987992317","https://openalex.org/W1990505856","https://openalex.org/W2000513720","https://openalex.org/W2018590636","https://openalex.org/W2024083195","https://openalex.org/W2049686551","https://openalex.org/W2074854222","https://openalex.org/W2075076415","https://openalex.org/W2093450784","https://openalex.org/W2093632031","https://openalex.org/W2102003408","https://openalex.org/W2104387086","https://openalex.org/W2111194146","https://openalex.org/W2134973740","https://openalex.org/W2164534744","https://openalex.org/W2188827208","https://openalex.org/W2408684684","https://openalex.org/W4251158933"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961","https://openalex.org/W334008168"],"abstract_inverted_index":{"We":[0,19,72],"propose":[1],"to":[2,7,43],"use":[3],"a":[4,21,65],"perceptually-oriented":[5],"domain":[6,47,112],"improve":[8],"the":[9,25,54,90,97,110,115],"quality":[10],"of":[11,53,64,67],"text-to-speech":[12],"generated":[13,87],"by":[14],"deep":[15],"neural":[16],"networks":[17],"(DNNs).":[18],"train":[20,73],"DNN":[22],"that":[23,58,75,109],"predicts":[24],"parameters":[26],"required":[27],"for":[28],"speech":[29,69,88,120],"reconstruction":[30],"but":[31],"whose":[32],"cost":[33,92],"function":[34,93],"is":[35,94],"calculated":[36],"in":[37,70,96],"another":[38],"domain.":[39],"In":[40],"this":[41,45],"paper,":[42],"represent":[44],"perceptual":[46,104,111],"we":[48],"extract":[49],"an":[50],"approximated":[51],"version":[52],"Spectro-Temporal":[55],"Excitation":[56],"Pattern":[57],"was":[59],"originally":[60],"proposed":[61],"as":[62],"part":[63],"model":[66],"hearing":[68],"noise.":[71],"DNNs":[74],"pre-dict":[76],"band":[77],"aperiodicity,":[78],"fundamental":[79],"frequency":[80],"and":[81,85],"Mel":[82,98],"cepstral":[83],"coefficients":[84],"compare":[86],"when":[89],"spectral":[91,125],"defined":[95],"cepstral,":[99],"warped":[100],"log":[101],"spec-trum":[102],"or":[103],"domains.":[105],"Objective":[106],"results":[107],"indicate":[108],"system":[113],"achieves":[114],"highest":[116],"quality.":[117],"Index":[118],"Terms:":[119],"synthesis,":[121],"DNN,":[122],"objective":[123],"measures,":[124],"analysis":[126]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}