{"id":"https://openalex.org/W3012282011","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023225","title":"Voice Conversion by Dual-Domain Bidirectional Long Short-Term Memory Networks with Temporal Attention","display_name":"Voice Conversion by Dual-Domain Bidirectional Long Short-Term Memory Networks with Temporal Attention","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3012282011","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023225","mag":"3012282011"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100729112","display_name":"Xiaokong Miao","orcid":"https://orcid.org/0000-0002-7335-8500"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaokong Miao","raw_affiliation_strings":["Army Engineering University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Army Engineering University, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085248515","display_name":"Meng Sun","orcid":"https://orcid.org/0000-0002-7435-3752"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Sun","raw_affiliation_strings":["Army Engineering University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Army Engineering University, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011581435","display_name":"Xiongwei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongwei Zhang","raw_affiliation_strings":["Army Engineering University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Army Engineering University, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100729112"],"corresponding_institution_ids":["https://openalex.org/I4210163363"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20763339,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10 4","issue":null,"first_page":"955","last_page":"959"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9986000061035156,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.988099992275238,"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/computer-science","display_name":"Computer science","score":0.8470450043678284},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.7474183440208435},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6602352857589722},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5751399397850037},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4952966272830963},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.48175835609436035},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45177382230758667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34316200017929077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8470450043678284},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.7474183440208435},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6602352857589722},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5751399397850037},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4952966272830963},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.48175835609436035},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45177382230758667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34316200017929077},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W854541894","https://openalex.org/W1509691205","https://openalex.org/W2064675550","https://openalex.org/W2086796102","https://openalex.org/W2107860279","https://openalex.org/W2114659828","https://openalex.org/W2133564696","https://openalex.org/W2156142001","https://openalex.org/W2157412983","https://openalex.org/W2179428711","https://openalex.org/W2294351487","https://openalex.org/W2471520273","https://openalex.org/W2517194566","https://openalex.org/W2518172956","https://openalex.org/W2527287547","https://openalex.org/W2613328025","https://openalex.org/W2747753032","https://openalex.org/W2802935216","https://openalex.org/W2891813127","https://openalex.org/W2899877258","https://openalex.org/W2937537592","https://openalex.org/W2939146114","https://openalex.org/W2942163674","https://openalex.org/W2949615363","https://openalex.org/W6603838645","https://openalex.org/W6623517193","https://openalex.org/W6679434410","https://openalex.org/W6696767757"],"related_works":["https://openalex.org/W2341338763","https://openalex.org/W2950183183","https://openalex.org/W2030799363","https://openalex.org/W2032415964","https://openalex.org/W2288425735","https://openalex.org/W2349923317","https://openalex.org/W2894081631","https://openalex.org/W2986063033","https://openalex.org/W2340348677","https://openalex.org/W2130799169"],"abstract_inverted_index":{"Voice":[0],"conversion(VC)":[1],"is":[2,26,55,72,82,108],"a":[3,29,75,86,104],"method":[4],"for":[5],"seeking":[6],"to":[7,27,37,45,88,94,110],"convert":[8],"one":[9],"speaker's":[10],"voice":[11,15],"into":[12],"another":[13],"person's":[14],"while":[16],"maintaining":[17],"the":[18,23,34,38,42,59,96,112,117,120,133],"content":[19],"unchanged.":[20],"One":[21],"of":[22,31,68,99,119],"key":[24],"steps":[25],"construct":[28],"mapping":[30,60],"features":[32],"from":[33],"source":[35],"speaker":[36],"target":[39],"speaker.":[40],"Given":[41],"strong":[43],"ability":[44],"model":[46],"contextual":[47],"information,":[48],"bidirectional":[49],"long":[50],"short-term":[51],"memory":[52],"network":[53],"(BLSTM)":[54],"usually":[56],"taken":[57,84],"as":[58,74,85],"tool.":[61],"In":[62,92],"this":[63],"paper,":[64],"an":[65],"improved":[66],"version":[67],"BLSTM,":[69,71],"dual-domain":[70,113],"considered":[73],"baseline":[76],"where":[77],"dynamic":[78],"time":[79],"warping":[80],"(DTW)":[81],"conventionally":[83],"tool":[87],"align":[89],"speech":[90],"frames.":[91],"order":[93],"alleviate":[95],"negative":[97],"impacts":[98],"temporal":[100],"misalignment":[101],"in":[102],"DTW,":[103],"casual":[105],"attention":[106],"mechanism":[107],"introduced":[109],"improve":[111],"BLSTM.":[114],"Experiments":[115],"demonstrated":[116],"effectiveness":[118],"proposed":[121],"approach":[122],"by":[123],"yielding":[124],"lower":[125],"mel-ceptral":[126],"distances":[127],"and":[128],"higer":[129],"MOS":[130],"scores":[131],"than":[132],"baselines.":[134]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}