{"id":"https://openalex.org/W2399908737","doi":"https://doi.org/10.1109/icassp.2016.7472751","title":"A speaker adaptation technique for Gaussian process regression based speech synthesis using feature space transform","display_name":"A speaker adaptation technique for Gaussian process regression based speech synthesis using feature space transform","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2399908737","doi":"https://doi.org/10.1109/icassp.2016.7472751","mag":"2399908737"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100703189/ATD100000413/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024181978","display_name":"Tomoki Koriyama","orcid":"https://orcid.org/0000-0002-8347-5604"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tomoki Koriyama","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017018881","display_name":"Syohei Oshio","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Syohei Oshio","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022405100","display_name":"Takao Kobayashi","orcid":"https://orcid.org/0000-0003-0387-8030"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takao Kobayashi","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024181978"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.02447751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"86","issue":null,"first_page":"5610","last_page":"5614"},"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/T10028","display_name":"Topic Modeling","score":0.9794999957084656,"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/T11309","display_name":"Music and Audio Processing","score":0.9786999821662903,"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":0.7170312404632568},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7037550806999207},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6858935356140137},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6654428243637085},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.579011082649231},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5670808553695679},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.5297285914421082},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5221612453460693},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5109971761703491},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.501230001449585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4942062199115753},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4465637803077698},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.42198118567466736},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3251996636390686},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1498563587665558},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08074748516082764}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7170312404632568},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7037550806999207},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6858935356140137},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6654428243637085},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.579011082649231},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5670808553695679},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.5297285914421082},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5221612453460693},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5109971761703491},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.501230001449585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4942062199115753},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4465637803077698},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.42198118567466736},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3251996636390686},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1498563587665558},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08074748516082764},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2016.7472751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50304887","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100703189","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100703189/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:t2r2.star.titech.ac.jp:50304887","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100703189","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100703189/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2399908737.pdf","grobid_xml":"https://content.openalex.org/works/W2399908737.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1492383498","https://openalex.org/W1580216809","https://openalex.org/W1591172823","https://openalex.org/W1599512239","https://openalex.org/W1600722501","https://openalex.org/W1861150963","https://openalex.org/W1965255698","https://openalex.org/W1984905644","https://openalex.org/W2000513720","https://openalex.org/W2049686551","https://openalex.org/W2100140000","https://openalex.org/W2100717696","https://openalex.org/W2102003408","https://openalex.org/W2121981798","https://openalex.org/W2146871184","https://openalex.org/W2153914468","https://openalex.org/W2294797155","https://openalex.org/W2394662942","https://openalex.org/W2402293227","https://openalex.org/W2605320104","https://openalex.org/W6634689341","https://openalex.org/W6635376843","https://openalex.org/W6675380101","https://openalex.org/W6696843773","https://openalex.org/W6712239235","https://openalex.org/W6713400536","https://openalex.org/W6736204136","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W2024201202","https://openalex.org/W2535215250","https://openalex.org/W2049083033","https://openalex.org/W290673751","https://openalex.org/W2017702615"],"abstract_inverted_index":{"In":[0,74],"this":[1],"paper,":[2],"we":[3,78],"propose":[4],"a":[5,58],"speaker":[6,42,109],"adaptation":[7,43,85,110],"technique":[8,104],"for":[9,45],"statistical":[10],"parametric":[11],"speech":[12,27,34,39,91],"synthesis":[13,28],"based":[14],"on":[15],"Gaussian":[16],"process":[17],"regression":[18],"(GPR).":[19],"Although":[20],"it":[21,63],"is":[22,54,57,64],"reported":[23],"that":[24,101],"the":[25,30,37,46,75,87,102,106],"GPR-based":[26,47,90],"improves":[29],"naturalness":[31],"of":[32,89,95],"synthetic":[33],"compared":[35],"with":[36],"HMM-based":[38,108],"synthesis,":[40],"any":[41],"techniques":[44],"one":[48],"have":[49],"not":[50],"been":[51],"established.":[52],"This":[53],"because":[55],"GPR":[56],"nonparametric":[59],"model":[60,72,84],"and":[61,97],"hence":[62],"impossible":[65],"to":[66,71,82],"directly":[67],"apply":[68],"linear":[69],"transforms":[70],"parameters.":[73],"proposed":[76,103],"technique,":[77],"introduce":[79],"feature-space":[80],"transform":[81],"achieve":[83],"in":[86],"framework":[88],"synthesis.":[92],"Experimental":[93],"results":[94],"objective":[96],"subjective":[98],"tests":[99],"show":[100],"outperforms":[105],"conventional":[107],"framework.":[111]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}