{"id":"https://openalex.org/W2402019113","doi":"https://doi.org/10.21437/interspeech.2015-368","title":"A perceptual investigation of wavelet-based decomposition of f0 for text-to-speech synthesis","display_name":"A perceptual investigation of wavelet-based decomposition of f0 for text-to-speech synthesis","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2402019113","doi":"https://doi.org/10.21437/interspeech.2015-368","mag":"2402019113"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-368","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/portal/en/publications/a-perceptual-investigation-of-waveletbased-decomposition-of-f0-for-texttospeech-synthesis(76c40d33-5d4f-4c20-8579-bd30c1a752ce).html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109494794","display_name":"Manuel Sam Ribeiro","orcid":"https://orcid.org/0000-0001-8096-2231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manuel Sam Ribeiro","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084488961","display_name":"Robert A. Clark","orcid":"https://orcid.org/0000-0002-4892-3619"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert A. J. Clark","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7807,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8952683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1586","last_page":"1590"},"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":0.9983999729156494,"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":0.9983000159263611,"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/naturalness","display_name":"Naturalness","score":0.8760155439376831},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7531219124794006},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5944008827209473},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5763433575630188},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5318776369094849},{"id":"https://openalex.org/keywords/continuous-wavelet-transform","display_name":"Continuous wavelet transform","score":0.4894222319126129},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4836646020412445},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.4832814037799835},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.46521973609924316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46226632595062256},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.4443577826023102},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41258472204208374},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38509732484817505},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.3406224846839905},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3206014931201935},{"id":"https://openalex.org/keywords/discrete-wavelet-transform","display_name":"Discrete wavelet transform","score":0.1720505952835083},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1389428973197937},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12889936566352844},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.118670254945755}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8760155439376831},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7531219124794006},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5944008827209473},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5763433575630188},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5318776369094849},{"id":"https://openalex.org/C95722684","wikidata":"https://www.wikidata.org/wiki/Q2622756","display_name":"Continuous wavelet transform","level":5,"score":0.4894222319126129},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4836646020412445},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.4832814037799835},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.46521973609924316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46226632595062256},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.4443577826023102},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41258472204208374},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38509732484817505},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.3406224846839905},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3206014931201935},{"id":"https://openalex.org/C46286280","wikidata":"https://www.wikidata.org/wiki/Q2414958","display_name":"Discrete wavelet transform","level":4,"score":0.1720505952835083},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1389428973197937},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12889936566352844},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.118670254945755},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2015-368","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/76c40d33-5d4f-4c20-8579-bd30c1a752ce","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/76c40d33-5d4f-4c20-8579-bd30c1a752ce","pdf_url":"https://www.research.ed.ac.uk/portal/en/publications/a-perceptual-investigation-of-waveletbased-decomposition-of-f0-for-texttospeech-synthesis(76c40d33-5d4f-4c20-8579-bd30c1a752ce).html","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:openaire/76c40d33-5d4f-4c20-8579-bd30c1a752ce","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/76c40d33-5d4f-4c20-8579-bd30c1a752ce","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Ribeiro, M S, Yamagishi, J & Clark, R A J 2015, A perceptual investigation of wavelet-based decomposition of f0 for text-to-speech synthesis. in INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association. International Speech Communication Association, pp. 1586-1590. < http://www.isca-speech.org/archive/interspeech_2015/i15_1586.html >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/76c40d33-5d4f-4c20-8579-bd30c1a752ce","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/76c40d33-5d4f-4c20-8579-bd30c1a752ce","pdf_url":"https://www.research.ed.ac.uk/portal/en/publications/a-perceptual-investigation-of-waveletbased-decomposition-of-f0-for-texttospeech-synthesis(76c40d33-5d4f-4c20-8579-bd30c1a752ce).html","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5810626578","display_name":null,"funder_award_id":"CRSII2 141903","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2402019113.pdf","grobid_xml":"https://content.openalex.org/works/W2402019113.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1517939602","https://openalex.org/W1540083112","https://openalex.org/W1961629950","https://openalex.org/W2029190953","https://openalex.org/W2049686551","https://openalex.org/W2067752346","https://openalex.org/W2073791162","https://openalex.org/W2108048146","https://openalex.org/W2127589467","https://openalex.org/W2130750986","https://openalex.org/W2188827208","https://openalex.org/W2296111744","https://openalex.org/W2395510410","https://openalex.org/W2395980997","https://openalex.org/W2600829178"],"related_works":["https://openalex.org/W119415662","https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2535215250","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440"],"abstract_inverted_index":{"The":[0],"Continuous":[1],"Wavelet":[2],"Transform":[3],"(CWT)":[4],"has":[5],"been":[6],"recently":[7],"proposed":[8],"to":[9,29,61,70,80],"model":[10,33],"f0":[11,37,53,77],"in":[12],"the":[13,26,34,63,81],"context":[14],"of":[15,45,65,99],"speech":[16],"synthesis.It":[17],"was":[18],"shown":[19],"that":[20,32,75],"systems":[21,31],"using":[22],"signal":[23,35,38],"decomposition":[24],"with":[25,54,68,90],"CWT":[27,82],"tend":[28],"outperform":[30],"directly.The":[36],"is":[39,78],"typically":[40],"decomposed":[41],"into":[42],"various":[43],"scales":[44],"differing":[46],"frequency.":[47],"In":[48],"these":[49],"experiments,":[50],"we":[51],"reconstruct":[52],"selected":[55],"frequencies":[56,94,104],"and":[57],"ask":[58],"native":[59],"listeners":[60],"judge":[62],"naturalness":[64],"synthesized":[66],"utterances":[67,89],"respect":[69],"natural":[71],"speech.":[72],"Results":[73],"indicate":[74],"HMM-generated":[76],"comparable":[79],"low":[83],"frequencies,":[84],"suggesting":[85],"it":[86],"mostly":[87,106],"generates":[88],"neutral":[91],"intonation.":[92],"Middle":[93],"achieve":[95],"very":[96,102],"high":[97,103],"levels":[98],"naturalness,":[100],"while":[101],"are":[105],"noise.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}