{"id":"https://openalex.org/W4386030067","doi":"https://doi.org/10.3390/s23167283","title":"Research on Speech Synthesis Based on Mixture Alignment Mechanism","display_name":"Research on Speech Synthesis Based on Mixture Alignment Mechanism","publication_year":2023,"publication_date":"2023-08-20","ids":{"openalex":"https://openalex.org/W4386030067","doi":"https://doi.org/10.3390/s23167283","pmid":"https://pubmed.ncbi.nlm.nih.gov/37631819"},"language":"en","primary_location":{"id":"doi:10.3390/s23167283","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23167283","pdf_url":"https://www.mdpi.com/1424-8220/23/16/7283/pdf?version=1692586686","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/23/16/7283/pdf?version=1692586686","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079798556","display_name":"Yan Deng","orcid":"https://orcid.org/0000-0002-0778-6144"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Deng","raw_affiliation_strings":["School of Computer, Electronics and Information, Guangxi University, Nanning 530004, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, Electronics and Information, Guangxi University, Nanning 530004, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059122235","display_name":"Ning Wu","orcid":"https://orcid.org/0000-0002-4951-6337"},"institutions":[{"id":"https://openalex.org/I4210128032","display_name":"Beibu Gulf University","ror":"https://ror.org/031j0at32","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210128032"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ning Wu","raw_affiliation_strings":["Key Laboratory of Beibu Gulf Offshore Engineering Equipment and Technology, Beibu Gulf University, Qinzhou 535011, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Beibu Gulf Offshore Engineering Equipment and Technology, Beibu Gulf University, Qinzhou 535011, China","institution_ids":["https://openalex.org/I4210128032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042410962","display_name":"Chengjun Qiu","orcid":"https://orcid.org/0009-0001-2264-8866"},"institutions":[{"id":"https://openalex.org/I4210128032","display_name":"Beibu Gulf University","ror":"https://ror.org/031j0at32","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210128032"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengjun Qiu","raw_affiliation_strings":["College of Mechanical Naval Architecture and Ocean Engineering, Beibu Gulf University, Qinzhou 535011, China","Guangxi Key Laboratory of Ocean Engineering Equipment and Technology, Qinzhou 535011, China"],"affiliations":[{"raw_affiliation_string":"College of Mechanical Naval Architecture and Ocean Engineering, Beibu Gulf University, Qinzhou 535011, China","institution_ids":["https://openalex.org/I4210128032"]},{"raw_affiliation_string":"Guangxi Key Laboratory of Ocean Engineering Equipment and Technology, Qinzhou 535011, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069796663","display_name":"Yan Chen","orcid":"https://orcid.org/0000-0002-9950-684X"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yan Chen","raw_affiliation_strings":["School of Computer, Electronics and Information, Guangxi University, Nanning 530004, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, Electronics and Information, Guangxi University, Nanning 530004, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100620849","display_name":"Xueshan Gao","orcid":"https://orcid.org/0000-0003-0656-9460"},"institutions":[{"id":"https://openalex.org/I4210128032","display_name":"Beibu Gulf University","ror":"https://ror.org/031j0at32","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210128032"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueshan Gao","raw_affiliation_strings":["College of Mechanical Naval Architecture and Ocean Engineering, Beibu Gulf University, Qinzhou 535011, China"],"affiliations":[{"raw_affiliation_string":"College of Mechanical Naval Architecture and Ocean Engineering, Beibu Gulf University, Qinzhou 535011, China","institution_ids":["https://openalex.org/I4210128032"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059122235","https://openalex.org/A5069796663"],"corresponding_institution_ids":["https://openalex.org/I150807315","https://openalex.org/I4210128032"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":0.5219,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71640841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"23","issue":"16","first_page":"7283","last_page":"7283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9961000084877014,"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/T10860","display_name":"Speech and Audio Processing","score":0.9926999807357788,"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/spectrogram","display_name":"Spectrogram","score":0.8831183910369873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7483530044555664},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6379064321517944},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5315268635749817},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5137837529182434},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4881227910518646},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48352479934692383},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4475456476211548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.434174507856369},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.41752079129219055},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.41301584243774414},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34679877758026123},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2169536054134369},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13803356885910034},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10707542300224304}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8831183910369873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483530044555664},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6379064321517944},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5315268635749817},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5137837529182434},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4881227910518646},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48352479934692383},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4475456476211548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.434174507856369},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.41752079129219055},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.41301584243774414},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34679877758026123},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2169536054134369},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13803356885910034},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10707542300224304},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008037","descriptor_name":"Linguistics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008037","descriptor_name":"Linguistics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008037","descriptor_name":"Linguistics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.3390/s23167283","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23167283","pdf_url":"https://www.mdpi.com/1424-8220/23/16/7283/pdf?version=1692586686","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:37631819","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37631819","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10457820","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10457820","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10457820/pdf/sensors-23-07283.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:0e0bf250c36a4c8abfe834140d1f3dbd","is_oa":true,"landing_page_url":"https://doaj.org/article/0e0bf250c36a4c8abfe834140d1f3dbd","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 23, Iss 16, p 7283 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/23/16/7283/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s23167283","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 23; Issue 16; Pages: 7283","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s23167283","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23167283","pdf_url":"https://www.mdpi.com/1424-8220/23/16/7283/pdf?version=1692586686","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4386030067.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W170732776","https://openalex.org/W349236604","https://openalex.org/W2107860279","https://openalex.org/W2133665775","https://openalex.org/W2194775991","https://openalex.org/W2767052532","https://openalex.org/W2946200149","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W3015282541","https://openalex.org/W3021636956","https://openalex.org/W3026874504","https://openalex.org/W3092028330","https://openalex.org/W3102725307","https://openalex.org/W3125481789","https://openalex.org/W3158762648","https://openalex.org/W3162673269","https://openalex.org/W3169905056","https://openalex.org/W3196308991","https://openalex.org/W3198533616","https://openalex.org/W4224612669","https://openalex.org/W4286950013","https://openalex.org/W4312308677","https://openalex.org/W4313260787","https://openalex.org/W4313466158","https://openalex.org/W4360770798","https://openalex.org/W4379618854","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6757079273","https://openalex.org/W6763832098","https://openalex.org/W6777694618","https://openalex.org/W6783867762","https://openalex.org/W6802142237"],"related_works":["https://openalex.org/W4379653318","https://openalex.org/W4213428484","https://openalex.org/W4310471687","https://openalex.org/W3177163058","https://openalex.org/W3127598333","https://openalex.org/W2970730223","https://openalex.org/W2946200149","https://openalex.org/W3203164699","https://openalex.org/W3161109662","https://openalex.org/W3153768731"],"abstract_inverted_index":{"In":[0,20],"recent":[1],"years,":[2],"deep":[3],"learning-based":[4],"speech":[5,18,28],"synthesis":[6,29],"has":[7],"attracted":[8],"a":[9,26,50,87,91],"lot":[10],"of":[11,81,101,108,134,174],"attention":[12],"from":[13],"the":[14,40,78,82,98,102,106,109,112,115,123,127,132,135,138,155,172],"machine":[15],"learning":[16],"and":[17,46,58,69,72,140,158,160],"communities.":[19],"this":[21],"paper,":[22],"we":[23],"propose":[24],"Mixture-TTS,":[25],"non-autoregressive":[27],"model":[30],"based":[31,53,89],"on":[32,54,90,137],"mixture":[33],"alignment":[34,41,57,61,152],"mechanism.":[35],"Mixture-TTS":[36,48,85,136,147,175],"aims":[37],"to":[38,75,96,111,163],"optimize":[39,97],"information":[42,80,153],"between":[43,154],"text":[44,156],"sequences":[45,157],"mel-spectrogram.":[47,103],"uses":[49],"linguistic":[51],"encoder":[52],"soft":[55],"phoneme-level":[56],"hard":[59],"word-level":[60,66],"approaches,":[62],"which":[63],"explicitly":[64],"extract":[65],"semantic":[67],"information,":[68],"introduce":[70],"pitch":[71],"energy":[73],"predictors":[74],"optimally":[76],"predict":[77],"rhythmic":[79],"audio.":[83,166],"Specifically,":[84],"introduces":[86],"post-net":[88,113],"five-layer":[92],"1D":[93],"convolution":[94],"network":[95],"reconfiguration":[99],"capability":[100],"We":[104,130],"connect":[105],"output":[107],"decoder":[110],"through":[114],"residual":[116],"network.":[117],"The":[118,167],"mel-spectrogram":[119],"is":[120,148,161,176],"converted":[121],"into":[122],"final":[124],"audio":[125],"by":[126],"HiFi-GAN":[128],"vocoder.":[129],"evaluate":[131],"performance":[133],"AISHELL3":[139],"LJSpeech":[141],"datasets.":[142],"Experimental":[143],"results":[144],"show":[145],"that":[146,171],"somewhat":[149],"better":[150],"in":[151],"mel-spectrogram,":[159],"able":[162],"achieve":[164],"high-quality":[165],"ablation":[168],"studies":[169],"demonstrate":[170],"structure":[173],"effective.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}