{"id":"https://openalex.org/W4375869034","doi":"https://doi.org/10.1109/icassp49357.2023.10094872","title":"Embedding a Differentiable Mel-Cepstral Synthesis Filter to a Neural Speech Synthesis System","display_name":"Embedding a Differentiable Mel-Cepstral Synthesis Filter to a Neural Speech Synthesis System","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869034","doi":"https://doi.org/10.1109/icassp49357.2023.10094872"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094872","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094872","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101948311","display_name":"Takenori Yoshimura","orcid":"https://orcid.org/0000-0003-3964-5677"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takenori Yoshimura","raw_affiliation_strings":["Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan","Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan","Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062895056","display_name":"Shinji Takaki","orcid":"https://orcid.org/0000-0001-7294-7699"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinji Takaki","raw_affiliation_strings":["Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan","Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan","Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016084389","display_name":"Kazuhiro Nakamura","orcid":"https://orcid.org/0000-0002-6095-8996"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuhiro Nakamura","raw_affiliation_strings":["Techno-Speech, Inc.,Department of Research and Development,Nagoya,Japan","Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Techno-Speech, Inc.,Department of Research and Development,Nagoya,Japan","institution_ids":[]},{"raw_affiliation_string":"Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049909008","display_name":"Keiichiro Oura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keiichiro Oura","raw_affiliation_strings":["Techno-Speech, Inc.,Department of Research and Development,Nagoya,Japan","Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Techno-Speech, Inc.,Department of Research and Development,Nagoya,Japan","institution_ids":[]},{"raw_affiliation_string":"Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086910479","display_name":"Yukiya Hono","orcid":"https://orcid.org/0000-0003-1245-8791"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yukiya Hono","raw_affiliation_strings":["Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan","Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002887879","display_name":"Kei Hashimoto","orcid":"https://orcid.org/0000-0002-9774-3657"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kei Hashimoto","raw_affiliation_strings":["Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan","Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023240652","display_name":"Yoshihiko Nankaku","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiko Nankaku","raw_affiliation_strings":["Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan","Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan","Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan","institution_ids":[]}]}],"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":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9966999888420105,"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/T11309","display_name":"Music and Audio Processing","score":0.9951000213623047,"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/computer-science","display_name":"Computer science","score":0.7368096709251404},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6819963455200195},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6530428528785706},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6362619400024414},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6144613027572632},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5691860318183899},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5591626167297363},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5331888198852539},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.5150501728057861},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4864940047264099},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.41304171085357666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34088361263275146},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.18396154046058655},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11529812216758728},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08426308631896973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7368096709251404},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6819963455200195},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6530428528785706},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6362619400024414},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6144613027572632},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5691860318183899},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5591626167297363},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5331888198852539},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5150501728057861},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4864940047264099},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.41304171085357666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34088361263275146},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.18396154046058655},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11529812216758728},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08426308631896973},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094872","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094872","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W349984566","https://openalex.org/W1522301498","https://openalex.org/W1527535554","https://openalex.org/W2019647239","https://openalex.org/W2048277372","https://openalex.org/W2064354100","https://openalex.org/W2106792148","https://openalex.org/W2128413412","https://openalex.org/W2136442985","https://openalex.org/W2145892079","https://openalex.org/W2338186431","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2963091184","https://openalex.org/W2984862052","https://openalex.org/W2990440871","https://openalex.org/W3000389243","https://openalex.org/W3015338123","https://openalex.org/W3015437531","https://openalex.org/W3041738652","https://openalex.org/W3092028330","https://openalex.org/W3095212898","https://openalex.org/W3123097577","https://openalex.org/W3130168980","https://openalex.org/W3142087749","https://openalex.org/W3170283647","https://openalex.org/W3187128306","https://openalex.org/W3190244907","https://openalex.org/W3204728450","https://openalex.org/W4292120191","https://openalex.org/W6631190155","https://openalex.org/W6681658904","https://openalex.org/W6703605055","https://openalex.org/W6755811826","https://openalex.org/W6769680054","https://openalex.org/W6769767169","https://openalex.org/W6771763809","https://openalex.org/W6782760101","https://openalex.org/W6783867762","https://openalex.org/W6784892142","https://openalex.org/W6792025129","https://openalex.org/W6796464841","https://openalex.org/W6842057974"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2766680336","https://openalex.org/W2133320490","https://openalex.org/W2387604097","https://openalex.org/W2787035864","https://openalex.org/W4289830142","https://openalex.org/W2373675101","https://openalex.org/W3150393935","https://openalex.org/W1497065097"],"abstract_inverted_index":{"This":[0],"paper":[1],"integrates":[2],"a":[3,9,49,64,98],"classic":[4],"mel-cepstral":[5,22,60],"synthesis":[6,13,23,61],"filter":[7,24,62],"into":[8],"modern":[10],"neural":[11,29],"speech":[12,18,44,95],"system":[14,79,93,100],"towards":[15],"end-to-end":[16,86],"controllable":[17],"synthesis.":[19],"Since":[20],"the":[21,33,40,59,71,77,91,109],"is":[25],"explicitly":[26],"embedded":[27],"in":[28,32,76,84,108],"waveform":[30,74],"models":[31,75],"proposed":[34,78,92],"system,":[35],"both":[36],"voice":[37],"characteristics":[38],"and":[39,53,66,73],"pitch":[41],"of":[42],"synthesized":[43],"are":[45,111],"highly":[46],"controlled":[47],"via":[48],"frequency":[50],"warping":[51],"parameter":[52],"fundamental":[54],"frequency,":[55],"respectively.":[56],"We":[57],"implement":[58],"as":[63],"differentiable":[65],"GPU-friendly":[67],"module":[68],"to":[69,80],"enable":[70],"acoustic":[72],"be":[81],"simultaneously":[82],"optimized":[83],"an":[85],"manner.":[87],"Experiments":[88],"show":[89],"that":[90],"improves":[94],"quality":[96],"from":[97],"baseline":[99],"maintaining":[101],"controllability.":[102],"The":[103],"core":[104],"PyTorch":[105],"modules":[106],"used":[107],"experiments":[110],"publicly":[112],"available":[113],"on":[114],"GitHub":[115],"<sup":[116],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[117],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[118],".":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}