{"id":"https://openalex.org/W4390463212","doi":"https://doi.org/10.1587/transinf.2023edp7039","title":"Speech Rhythm-Based Speaker Embeddings Extraction from Phonemes and Phoneme Duration for Multi-Speaker Speech Synthesis","display_name":"Speech Rhythm-Based Speaker Embeddings Extraction from Phonemes and Phoneme Duration for Multi-Speaker Speech Synthesis","publication_year":2023,"publication_date":"2023-12-31","ids":{"openalex":"https://openalex.org/W4390463212","doi":"https://doi.org/10.1587/transinf.2023edp7039"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2023edp7039","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2023edp7039","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/1/E107.D_2023EDP7039/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/1/E107.D_2023EDP7039/_pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015668532","display_name":"Kenichi FUJITA","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenichi FUJITA","raw_affiliation_strings":["NTT Human Informatics Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Human Informatics Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103279502","display_name":"Atsushi Ando","orcid":"https://orcid.org/0000-0003-1586-0356"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi ANDO","raw_affiliation_strings":["NTT Human Informatics Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Human Informatics Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046709969","display_name":"Yusuke Ijima","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke IJIMA","raw_affiliation_strings":["NTT Human Informatics Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Human Informatics Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.3173,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6509546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"E107.D","issue":"1","first_page":"93","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9886000156402588,"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":0.9837999939918518,"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/speech-recognition","display_name":"Speech recognition","score":0.7859607934951782},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7660260796546936},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.5861414074897766},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5734055042266846},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5632993578910828},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5619248747825623},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.46189889311790466},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.45888668298721313},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43254414200782776},{"id":"https://openalex.org/keywords/closeness","display_name":"Closeness","score":0.41828542947769165},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4146740734577179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.382324755191803},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3365844190120697},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12065830826759338},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.0865027904510498}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7859607934951782},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7660260796546936},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.5861414074897766},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5734055042266846},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5632993578910828},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5619248747825623},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46189889311790466},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.45888668298721313},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43254414200782776},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.41828542947769165},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4146740734577179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.382324755191803},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3365844190120697},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12065830826759338},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0865027904510498},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1587/transinf.2023edp7039","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2023edp7039","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/1/E107.D_2023EDP7039/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2402.07085","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.07085","pdf_url":"https://arxiv.org/pdf/2402.07085","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1587/transinf.2023edp7039","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2023edp7039","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/1/E107.D_2023EDP7039/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4390463212.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1492383498","https://openalex.org/W1596753861","https://openalex.org/W1655137980","https://openalex.org/W1692058958","https://openalex.org/W2019835243","https://openalex.org/W2030361736","https://openalex.org/W2102003408","https://openalex.org/W2114925438","https://openalex.org/W2150769028","https://openalex.org/W2165700458","https://openalex.org/W2398431249","https://openalex.org/W2402146185","https://openalex.org/W2619368999","https://openalex.org/W2746498480","https://openalex.org/W2787685498","https://openalex.org/W2794490148","https://openalex.org/W2808706139","https://openalex.org/W2887171382","https://openalex.org/W2890964092","https://openalex.org/W2896457183","https://openalex.org/W2962959915","https://openalex.org/W2963371159","https://openalex.org/W2964243274","https://openalex.org/W2964247977","https://openalex.org/W2972595148","https://openalex.org/W2972743990","https://openalex.org/W3013020904","https://openalex.org/W3015826515","https://openalex.org/W3016136182","https://openalex.org/W3030163527","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3131643166","https://openalex.org/W3161296985","https://openalex.org/W3197830622","https://openalex.org/W3209059054","https://openalex.org/W4205234379","https://openalex.org/W4235154690","https://openalex.org/W4301306964"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,15,77,112],"speech":[4,45,95,140,142],"rhythm-based":[5,56],"method":[6,53,110,137],"for":[7,40],"speaker":[8,31,78,92,114,148],"embeddings":[9,57,93,157,167,190],"to":[10,67,70,82,104,145,158],"model":[11,80],"phoneme":[12],"duration":[13,125],"using":[14],"few":[16],"utterances":[17,43],"by":[18],"the":[19,27,51,55,83,106,135,146,150,156,160,163,166,169,175,179,183,187,192],"target":[20,147],"speaker.":[21],"Speech":[22],"rhythm":[23,143],"is":[24,54],"one":[25],"of":[26,50,165,174,189],"essential":[28],"factors":[29],"among":[30],"characteristics,":[32],"along":[33],"with":[34,76,97,120,141],"acoustic":[35],"features":[36],"such":[37],"as":[38],"F0,":[39],"reproducing":[41],"individual":[42],"in":[44],"synthesis.":[46],"A":[47],"novel":[48],"feature":[49],"proposed":[52,109,136],"extracted":[58,75],"from":[59],"phonemes":[60,122],"and":[61,100,123,129,168,178,194],"their":[62,124],"durations,":[63],"which":[64],"are":[65,74],"known":[66],"be":[68],"related":[69],"speaking":[71],"rhythm.":[72],"They":[73],"identification":[79,115],"similar":[81],"conventional":[84,151],"spectral":[85],"feature-based":[86],"one.":[87],"We":[88,153],"conducted":[89],"three":[90],"experiments,":[91],"generation,":[94],"synthesis":[96],"generated":[98],"embeddings,":[99],"embedding":[101,176],"space":[102,177],"analysis,":[103],"evaluate":[105,159],"performance.":[107],"The":[108,127,172],"demonstrated":[111,133],"moderate":[113],"performance":[116],"(15.2%":[117],"EER),":[118],"even":[119],"only":[121],"information.":[126],"objective":[128,195],"subjective":[130,193],"evaluation":[131],"results":[132],"that":[134,186],"can":[138],"synthesize":[139],"closer":[144],"than":[149],"method.":[152],"also":[154],"visualized":[155],"relationship":[161],"between":[162,182],"distance":[164],"perceptual":[170],"similarity.":[171,196],"visualization":[173],"relation":[180],"analysis":[181],"closeness":[184],"indicated":[185],"distribution":[188],"reflects":[191]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-01-24T23:23:39.755997","created_date":"2025-10-10T00:00:00"}