{"id":"https://openalex.org/W51262010","doi":"https://doi.org/10.21437/interspeech.2004-461","title":"DFW-based spectral smoothing for concatenative speech synthesis","display_name":"DFW-based spectral smoothing for concatenative speech synthesis","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W51262010","doi":"https://doi.org/10.21437/interspeech.2004-461","mag":"51262010"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-461","doi":"https://doi.org/10.21437/interspeech.2004-461","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-461","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5009130244","display_name":"Hartmut R. Pfitzinger","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hartmut R. Pfitzinger","raw_affiliation_strings":["Advanced Telecommunications Research Institute International"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Telecommunications Research Institute International","institution_ids":["https://openalex.org/I4210104143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5009130244"],"corresponding_institution_ids":["https://openalex.org/I4210104143"],"apc_list":null,"apc_paid":null,"fwci":0.7123,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.62746327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"1397","last_page":"1400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.975600004196167,"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":0.975600004196167,"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":0.021900000050663948,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0010000000474974513,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectral-smoothing","display_name":"spectral smoothing","score":0.9179999828338623},{"id":"https://openalex.org/keywords/concatenative-speech-synthesis","display_name":"concatenative speech synthesis","score":0.9089999794960022},{"id":"https://openalex.org/keywords/spectral-interpolation","display_name":"spectral interpolation","score":0.4699999988079071},{"id":"https://openalex.org/keywords/dynamic-programming-alignment","display_name":"dynamic programming alignment","score":0.7879999876022339},{"id":"https://openalex.org/keywords/autocorrelation-coefficient","display_name":"autocorrelation coefficient","score":0.6060000061988831}],"concepts":[{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.7490217685699463},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6889730095863342},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.6702329516410828},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5225576758384705},{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.5186387896537781},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49217572808265686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48880574107170105},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.47148701548576355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.46830642223358154},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.45841193199157715},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.4139360785484314},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.383194237947464},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.38257724046707153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2077830731868744},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12141454219818115},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.12129810452461243},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08561789989471436},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2004-461","doi":"https://doi.org/10.21437/interspeech.2004-461","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-461","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.67.7911","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.67.7911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.phonetik.uni-muenchen.de/~hpt/pub/Pfitzinger_ICSLP04.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W155300571","https://openalex.org/W1505932402","https://openalex.org/W1510007267","https://openalex.org/W1560642549","https://openalex.org/W1652807356","https://openalex.org/W1966264494","https://openalex.org/W2022554507","https://openalex.org/W2033516035","https://openalex.org/W2047268084","https://openalex.org/W2131456521","https://openalex.org/W2150307531","https://openalex.org/W2167745106","https://openalex.org/W2171015304","https://openalex.org/W2405069075"],"related_works":["https://openalex.org/W2131456521","https://openalex.org/W2401630197","https://openalex.org/W2116873759","https://openalex.org/W4247766375","https://openalex.org/W2141368411","https://openalex.org/W3140198813","https://openalex.org/W2111748458","https://openalex.org/W24778232","https://openalex.org/W2535081697","https://openalex.org/W134995353"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"and":[3,50,84],"evaluates":[4],"a":[5,33],"new":[6],"spectral":[7,21,69,86],"smoothing":[8],"technique":[9],"whose":[10,25,88],"performance":[11],"is":[12,98],"comparable":[13],"with":[14,104],"LSP":[15],"interpolation":[16,79],"in":[17],"terms":[18],"of":[19,36,108],"Euclidean":[20],"distance":[22],"measurements":[23],"but":[24],"interpolated":[26],"formant":[27],"trajectories":[28],"are":[29,74],"more":[30],"reasonable":[31],"from":[32,46],"phonetic":[34],"point":[35],"view.":[37],"The":[38],"approach":[39],"firstly":[40],"estimates":[41],"derivative":[42],"logarithmic":[43],"magnitude":[44],"spectra":[45],"both":[47],"the":[48,51,63,81,96,105],"source":[49,83],"target":[52,85],"frame":[53],"represented":[54],"by":[55,76,92],"autoregressive":[56,101],"filter":[57,102],"coefficients.":[58,110],"Then,":[59],"Dynamic":[60],"Programming":[61],"yields":[62],"best":[64],"alignment":[65,89],"between":[66,80],"these":[67],"two":[68],"representations.":[70],"Smoothed":[71],"frequency":[72],"responses":[73],"achieved":[75],"weighted":[77],"linear":[78],"corresponding":[82],"lines":[87],"was":[90],"found":[91],"DP":[93],"backtracking.":[94],"Finally,":[95],"spectrum":[97],"converted":[99],"to":[100],"coefficients":[103],"intermediate":[106],"stage":[107],"autocorrelation":[109],"1.":[111]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-10-07T09:51:55.459714","created_date":"2016-06-24T00:00:00"}