{"id":"https://openalex.org/W3197541421","doi":"https://doi.org/10.21437/interspeech.2021-866","title":"FastPitchFormant: Source-Filter Based Decomposed Modeling for Speech Synthesis","display_name":"FastPitchFormant: Source-Filter Based Decomposed Modeling for Speech Synthesis","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197541421","doi":"https://doi.org/10.21437/interspeech.2021-866","mag":"3197541421"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-866","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5073688244","display_name":"Taejun Bak","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Taejun Bak","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060429696","display_name":"Jae\u2010sung Bae","orcid":"https://orcid.org/0000-0002-8270-0072"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jae-Sung Bae","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046330926","display_name":"Hanbin Bae","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanbin Bae","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026954673","display_name":"Young-Ik Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Young-Ik Kim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052468556","display_name":"Hoon Young Cho","orcid":"https://orcid.org/0000-0002-6850-6580"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoon-Young Cho","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073688244"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2237,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.83405737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"116","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962000250816345,"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":0.9962000250816345,"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":0.9886999726295471,"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":0.9646000266075134,"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/computer-science","display_name":"Computer science","score":0.7016218304634094},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5152435898780823},{"id":"https://openalex.org/keywords/source-model","display_name":"Source model","score":0.5024869441986084},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4718741476535797},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4648268520832062},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.09631669521331787},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07551869750022888}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7016218304634094},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5152435898780823},{"id":"https://openalex.org/C2985998994","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Source model","level":2,"score":0.5024869441986084},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4718741476535797},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4648268520832062},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.09631669521331787},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07551869750022888}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-866","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Methods":[0],"for":[1,12],"modeling":[2,80],"and":[3,39,74],"controlling":[4],"prosody":[5],"with":[6,29],"acoustic":[7,24,75],"features":[8,76,94],"have":[9],"been":[10],"proposed":[11],"neural":[13],"text-to-speech":[14],"(TTS)":[15],"models.":[16],"Prosodic":[17],"speech":[18,28],"can":[19,95],"be":[20,96],"generated":[21],"by":[22],"conditioning":[23],"features.":[25],"However,":[26],"synthesized":[27],"a":[30,49,68],"large":[31],"pitch-shift":[32],"scale":[33],"suffers":[34],"from":[35],"audio":[36],"quality":[37],"degradation,":[38],"speaker":[40],"characteristics":[41],"deformation.":[42],"To":[43],"address":[44],"this":[45],"problem,":[46],"we":[47],"propose":[48],"feed-forward":[50],"Transformer":[51],"based":[52,58],"TTS":[53],"model":[54,88],"that":[55,71,86],"is":[56],"designed":[57],"on":[59],"the":[60,84,87,90],"source-filter":[61],"theory.":[62],"This":[63],"model,":[64],"called":[65],"FastPitchFormant,":[66],"has":[67],"unique":[69],"structure":[70],"handles":[72],"text":[73],"in":[77],"parallel.":[78],"With":[79],"each":[81],"feature":[82],"separately,":[83],"tendency":[85],"learns":[89],"relationship":[91],"between":[92],"two":[93],"mitigated.":[97]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
