{"id":"https://openalex.org/W4393657127","doi":"https://doi.org/10.1109/o-cocosda60357.2023.10482964","title":"Comparative Analysis of Direct Speech-to-Speech Translation and Voice Conversion Using Bi-LSTM","display_name":"Comparative Analysis of Direct Speech-to-Speech Translation and Voice Conversion Using Bi-LSTM","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4393657127","doi":"https://doi.org/10.1109/o-cocosda60357.2023.10482964"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda60357.2023.10482964","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/o-cocosda60357.2023.10482964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5020245577","display_name":"Lalaram Arya","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Lalaram Arya","raw_affiliation_strings":["Indian Institute of Technology Dharwad,Department of Electrical Engineering,Dharwad,India,580011"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Dharwad,Department of Electrical Engineering,Dharwad,India,580011","institution_ids":["https://openalex.org/I4210152718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094342810","display_name":"Sai Naga Venu Gopal Bhamidi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sai Naga Venu Gopal Bhamidi","raw_affiliation_strings":["Indian Institute of Technology Dharwad,Department of Electrical Engineering,Dharwad,India,580011"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Dharwad,Department of Electrical Engineering,Dharwad,India,580011","institution_ids":["https://openalex.org/I4210152718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108704314","display_name":"Shashi Prabha","orcid":"https://orcid.org/0009-0002-0408-0653"},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shashi Prabha","raw_affiliation_strings":["Indian Institute of Technology Dharwad,Department of Electrical Engineering,Dharwad,India,580011"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Dharwad,Department of Electrical Engineering,Dharwad,India,580011","institution_ids":["https://openalex.org/I4210152718"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052129812","display_name":"S. R. Mahadeva Prasanna","orcid":"https://orcid.org/0000-0002-8135-7938"},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. R. Mahadeva Prasanna","raw_affiliation_strings":["Indian Institute of Technology Dharwad,Department of Electrical Engineering,Dharwad,India,580011"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Dharwad,Department of Electrical Engineering,Dharwad,India,580011","institution_ids":["https://openalex.org/I4210152718"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210152718"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26310809,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"77","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9639999866485596,"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":0.9639999866485596,"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/speech-recognition","display_name":"Speech recognition","score":0.7503316402435303},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7288661003112793},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.6440151929855347},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5048499703407288},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4888607859611511},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4780624210834503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4241119623184204},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42174625396728516},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3006962537765503},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.049815356731414795}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7503316402435303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7288661003112793},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6440151929855347},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5048499703407288},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4888607859611511},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4780624210834503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4241119623184204},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42174625396728516},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3006962537765503},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.049815356731414795},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda60357.2023.10482964","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/o-cocosda60357.2023.10482964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1509691205","https://openalex.org/W1510746193","https://openalex.org/W1579847400","https://openalex.org/W1969443802","https://openalex.org/W1993882792","https://openalex.org/W2005708641","https://openalex.org/W2051745966","https://openalex.org/W2064675550","https://openalex.org/W2081592734","https://openalex.org/W2086796102","https://openalex.org/W2120605154","https://openalex.org/W2121387787","https://openalex.org/W2126143605","https://openalex.org/W2131774270","https://openalex.org/W2135708429","https://openalex.org/W2136545725","https://openalex.org/W2136922672","https://openalex.org/W2145095987","https://openalex.org/W2146173057","https://openalex.org/W2605131327","https://openalex.org/W2972495969","https://openalex.org/W3007068036","https://openalex.org/W3017535695","https://openalex.org/W3142316150","https://openalex.org/W3180374548","https://openalex.org/W4213198175","https://openalex.org/W4313203218","https://openalex.org/W4328054436"],"related_works":["https://openalex.org/W2883671469","https://openalex.org/W2338806053","https://openalex.org/W4385571610","https://openalex.org/W2293738010","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W4360995948","https://openalex.org/W1909292483","https://openalex.org/W1428730622"],"abstract_inverted_index":{"This":[0,129],"study":[1,86],"aims":[2,46],"to":[3,11,47,82,123,133,151,163,180],"conduct":[4],"a":[5,20,73,84],"comparative":[6,85],"analysis":[7],"between":[8,35,87],"Direct":[9],"Speech":[10,12],"Translation":[13],"(DS2ST)":[14],"and":[15,38,70,90,99,105,141,154],"Voice":[16],"Conversion":[17],"(VC)":[18],"utilizing":[19],"Bi-Directional":[21],"Long":[22],"Short-Term":[23],"Memory":[24],"(Bi-LSTM)":[25],"network.":[26],"The":[27,109],"process":[28],"in":[29,165,171],"VC":[30,89,98,113],"entails":[31],"mapping":[32],"speaker-specific":[33],"characteristics":[34],"the":[36,42,62,88,97,103,107,126,134,137,148,157,166,172],"target":[37],"source":[39],"speakers.":[40],"On":[41],"other":[43],"hand,":[44],"DS2ST":[45,91,100,124],"map":[48],"linguistic":[49],"information":[50,140],"of":[51,53,120,168,174],"speech":[52],"two":[54],"different":[55],"spoken":[56],"languages,":[57],"which":[58],"may":[59,79,130],"be":[60,80,115,131],"for":[61],"same":[63],"speaker.":[64],"Since":[65],"both":[66],"involve":[67],"similar":[68],"strategies":[69],"there":[71],"is":[72,177],"rich":[74],"literature":[75],"on":[76],"VC,":[77,175],"it":[78,176],"appropriate":[81],"do":[83],"frameworks.":[92],"Accordingly,":[93],"this":[94],"work":[95],"develops":[96],"model":[101],"using":[102,125],"Bi-LSTM":[104,127],"analyzes":[106],"research.":[108],"findings":[110],"reveal":[111],"that":[112,156],"can":[114],"performed":[116],"with":[117],"less":[118],"number":[119],"layers":[121,153],"compared":[122],"model.":[128],"attributed":[132],"differences":[135],"among":[136],"speaker":[138],"specific":[139],"sound":[142],"unit":[143],"information.":[144],"We":[145],"have":[146],"evaluated":[147],"system":[149],"up":[150],"four":[152],"found":[155],"MCD":[158],"value":[159],"improves":[160],"from":[161,178],"7.484":[162],"6.061":[164],"case":[167,173],"DS2ST,":[169],"while":[170],"5.549":[179],"5.370.":[181]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}