{"id":"https://openalex.org/W2964041258","doi":"https://doi.org/10.1109/icassp.2019.8683791","title":"STFT Spectral Loss for Training a Neural Speech Waveform Model","display_name":"STFT Spectral Loss for Training a Neural Speech Waveform Model","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2964041258","doi":"https://doi.org/10.1109/icassp.2019.8683791","mag":"2964041258"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/08fac827-33f6-4d83-9b91-2a35538a6030","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062895056","display_name":"Shinji Takaki","orcid":"https://orcid.org/0000-0001-7294-7699"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinji Takaki","raw_affiliation_strings":["National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041887072","display_name":"Toru Nakashika","orcid":"https://orcid.org/0000-0003-1863-6771"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toru Nakashika","raw_affiliation_strings":["The University of Electro-Communications, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7065","last_page":"7069"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991999864578247,"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/T10320","display_name":"Neural Networks and Applications","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.9389230012893677},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7006751894950867},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6166121363639832},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5406650304794312},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.5292869210243225},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.4349375069141388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40690526366233826},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33241939544677734},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1698056161403656},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.15152794122695923},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07201531529426575}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.9389230012893677},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7006751894950867},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6166121363639832},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5406650304794312},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.5292869210243225},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.4349375069141388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40690526366233826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33241939544677734},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1698056161403656},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.15152794122695923},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07201531529426575},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2019.8683791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/08fac827-33f6-4d83-9b91-2a35538a6030","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/08fac827-33f6-4d83-9b91-2a35538a6030","pdf_url":"https://www.research.ed.ac.uk/en/publications/08fac827-33f6-4d83-9b91-2a35538a6030","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Takaki, S, Nakashika, T, Wang, X & Yamagishi, J 2019, STFT Spectral Loss for Training a Neural Speech Waveform Model. in ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, Brighton, United Kingdom, pp. 7065-7069, 44th International Conference on Acoustics, Speech, and Signal Processing, Brighton , United Kingdom, 12/05/19. https://doi.org/10.1109/ICASSP.2019.8683791","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/08fac827-33f6-4d83-9b91-2a35538a6030","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/08fac827-33f6-4d83-9b91-2a35538a6030","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Takaki, S, Nakashika, T, Wang, X & Yamagishi, J 2019, STFT Spectral Loss for Training a Neural Speech Waveform Model. in ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, Brighton, United Kingdom, pp. 7065-7069, 44th International Conference on Acoustics, Speech, and Signal Processing, Brighton , United Kingdom, 12/05/19. https://doi.org/10.1109/ICASSP.2019.8683791","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/08fac827-33f6-4d83-9b91-2a35538a6030","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/08fac827-33f6-4d83-9b91-2a35538a6030","pdf_url":"https://www.research.ed.ac.uk/en/publications/08fac827-33f6-4d83-9b91-2a35538a6030","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Takaki, S, Nakashika, T, Wang, X & Yamagishi, J 2019, STFT Spectral Loss for Training a Neural Speech Waveform Model. in ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, Brighton, United Kingdom, pp. 7065-7069, 44th International Conference on Acoustics, Speech, and Signal Processing, Brighton , United Kingdom, 12/05/19. https://doi.org/10.1109/ICASSP.2019.8683791","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2964041258.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W1504438288","https://openalex.org/W1522301498","https://openalex.org/W2016589492","https://openalex.org/W2087316977","https://openalex.org/W2135029798","https://openalex.org/W2337957568","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2749651610","https://openalex.org/W2749881488","https://openalex.org/W2769810959","https://openalex.org/W2801493797","https://openalex.org/W2963175743","https://openalex.org/W2963522141","https://openalex.org/W2963782041","https://openalex.org/W2963975282","https://openalex.org/W2964121744","https://openalex.org/W2964195110","https://openalex.org/W2964243274","https://openalex.org/W4294619240","https://openalex.org/W6603838645","https://openalex.org/W6631190155","https://openalex.org/W6680012447","https://openalex.org/W6753855596"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2176409448","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2364769705","https://openalex.org/W4225639054","https://openalex.org/W4200633555","https://openalex.org/W1967434260","https://openalex.org/W2115073044","https://openalex.org/W4313577963"],"abstract_inverted_index":{"This":[0],"paper":[1,95],"proposes":[2],"a":[3,17,97],"new":[4],"loss":[5,67],"using":[6],"short-time":[7],"Fourier":[8],"transform":[9],"(STFT)":[10],"spectra":[11,34,38,81],"for":[12],"the":[13,48,58,62,65,77,102,123],"aim":[14],"of":[15,57,64,82,109],"training":[16,56,74],"high-performance":[18],"neural":[19,125],"speech":[20,27,42,84,103,129],"waveform":[21,28,59,104],"model":[22,60,126],"that":[23,55,75,122],"predicts":[24],"raw":[25],"continuous":[26],"samples":[29],"directly.":[30],"Not":[31],"only":[32],"amplitude":[33,78],"but":[35],"also":[36,52],"phase":[37,80],"obtained":[39],"from":[40],"generated":[41,83],"waveforms":[43,85],"are":[44],"used":[45],"to":[46],"calculate":[47],"proposed":[49,66,124],"loss.":[50],"We":[51],"mathematically":[53],"show":[54],"on":[61],"basis":[63],"can":[68],"be":[69],"interpreted":[70],"as":[71,101],"maximum":[72],"likelihood":[73],"assumes":[76],"and":[79,88,115],"following":[86],"Gaussian":[87],"von":[89],"Mises":[90],"distributions,":[91],"respectively.":[92],"Furthermore,":[93],"this":[94],"presents":[96],"simple":[98],"network":[99],"architecture":[100],"model,":[105],"which":[106],"is":[107],"composed":[108],"uni-directional":[110],"long":[111],"short-term":[112],"memories":[113],"(LSTMs)":[114],"an":[116],"auto-regressive":[117],"structure.":[118],"Experimental":[119],"results":[120],"showed":[121],"synthesized":[127],"high-quality":[128],"waveforms.":[130]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}