{"id":"https://openalex.org/W1990383786","doi":"https://doi.org/10.1109/globalsip.2014.7032177","title":"Modified post-filter to recover modulation spectrum for HMM-based speech synthesis","display_name":"Modified post-filter to recover modulation spectrum for HMM-based speech synthesis","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1990383786","doi":"https://doi.org/10.1109/globalsip.2014.7032177","mag":"1990383786"},"language":"en","primary_location":{"id":"doi:10.1109/globalsip.2014.7032177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2014.7032177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","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/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["JP","US"],"is_corresponding":true,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Japan","Language Technologies Institute, Carnegie Mellon University (CMU), U.S.A"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University (CMU), U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan W Black","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University (CMU), U.S.A"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University (CMU), U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013050263"],"corresponding_institution_ids":["https://openalex.org/I74973139","https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":1.636,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8673395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"547","last_page":"551"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9959999918937683,"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":0.9818999767303467,"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/speech-recognition","display_name":"Speech recognition","score":0.7294853329658508},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6845735907554626},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6374675035476685},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6164017915725708},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5393846035003662},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5327805280685425},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4190077483654022},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3360660970211029},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12609878182411194}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7294853329658508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6845735907554626},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6374675035476685},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6164017915725708},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5393846035003662},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5327805280685425},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4190077483654022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3360660970211029},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12609878182411194}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globalsip.2014.7032177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2014.7032177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W92302539","https://openalex.org/W187033940","https://openalex.org/W1523372075","https://openalex.org/W1600722501","https://openalex.org/W1935012542","https://openalex.org/W1984905644","https://openalex.org/W1987992317","https://openalex.org/W1990505856","https://openalex.org/W1992228106","https://openalex.org/W2000513720","https://openalex.org/W2005768155","https://openalex.org/W2029434926","https://openalex.org/W2039800941","https://openalex.org/W2049367655","https://openalex.org/W2049686551","https://openalex.org/W2075012882","https://openalex.org/W2095437083","https://openalex.org/W2106792148","https://openalex.org/W2109444541","https://openalex.org/W2111284386","https://openalex.org/W2142183264","https://openalex.org/W2142813692","https://openalex.org/W2154920538","https://openalex.org/W2159528802","https://openalex.org/W2170580867","https://openalex.org/W2395578248","https://openalex.org/W2917245127","https://openalex.org/W4301420498","https://openalex.org/W6607663849","https://openalex.org/W6631309588","https://openalex.org/W6677973343","https://openalex.org/W6680796965","https://openalex.org/W6683640347","https://openalex.org/W6711777497"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W2333799855","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,8,96,108],"modified":[4,89,132],"post-filter":[5,34,60,104,118],"to":[6,54,64,107,119],"recover":[7,120],"Modulation":[9],"Spectrum":[10],"(MS)":[11],"in":[12,28,139],"HMM-based":[13,29],"speech":[14,30,46,68,141],"synthesis.":[15],"To":[16,82],"alleviate":[17],"the":[18,25,32,40,44,55,92,102,117,121,131,145],"over-smoothing":[19],"effect":[20],"which":[21,76,105],"is":[22,61],"one":[23],"of":[24,43,67,124],"major":[26],"problems":[27],"synthesis,":[31],"MS-based":[33],"has":[35],"been":[36],"proposed.":[37],"It":[38],"recovers":[39],"utterance-level":[41],"MS":[42,123],"generated":[45],"trajectory,":[47],"and":[48,100],"we":[49,86,113],"have":[50],"reported":[51],"its":[52],"benefit":[53],"quality":[56,137],"improvement.":[57],"However,":[58],"this":[59,84],"not":[62],"applicable":[63,106],"various":[65],"lengths":[66],"parameter":[69,110],"trajectories,":[70],"such":[71],"as":[72,142],"phrases":[73],"or":[74],"segments,":[75],"are":[77],"shorter":[78],"than":[79],"an":[80],"utterance.":[81],"address":[83],"problem,":[85],"propose":[87,115],"two":[88],"post-filters,":[90],"(1)":[91],"time-invariant":[93],"filter":[94],"with":[95],"simplified":[97],"conversion":[98],"form":[99],"(2)":[101],"segment-level":[103],"short-term":[109],"sequence.":[111],"Furthermore,":[112],"also":[114,134],"(3)":[116],"phoneme-level":[122],"HMM-state":[125],"duration.":[126],"Experimental":[127],"results":[128],"show":[129],"that":[130],"post-filters":[133],"yield":[135],"significant":[136],"improvements":[138],"synthetic":[140],"yielded":[143],"by":[144],"conventional":[146],"post-filter.":[147]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}