{"id":"https://openalex.org/W4404032920","doi":"https://doi.org/10.1109/icccnt61001.2024.10725517","title":"Innovations in Real-Time Speech Translation: Leveraging Griffin-Lim Algorithm","display_name":"Innovations in Real-Time Speech Translation: Leveraging Griffin-Lim Algorithm","publication_year":2024,"publication_date":"2024-06-24","ids":{"openalex":"https://openalex.org/W4404032920","doi":"https://doi.org/10.1109/icccnt61001.2024.10725517"},"language":"en","primary_location":{"id":"doi:10.1109/icccnt61001.2024.10725517","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt61001.2024.10725517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT)","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/A5114512255","display_name":"Himanshu Maithani","orcid":null},"institutions":[{"id":"https://openalex.org/I145286018","display_name":"SRM Institute of Science and Technology","ror":"https://ror.org/050113w36","country_code":"IN","type":"education","lineage":["https://openalex.org/I145286018"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Himanshu Maithani","raw_affiliation_strings":["SRM Institute of Science and Technology,Computing Technologies,Chennai,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRM Institute of Science and Technology,Computing Technologies,Chennai,India","institution_ids":["https://openalex.org/I145286018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110172618","display_name":"A. Goswami","orcid":"https://orcid.org/0009-0000-2971-2763"},"institutions":[{"id":"https://openalex.org/I145286018","display_name":"SRM Institute of Science and Technology","ror":"https://ror.org/050113w36","country_code":"IN","type":"education","lineage":["https://openalex.org/I145286018"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aditya Giri Goswami","raw_affiliation_strings":["SRM Institute of Science and Technology,Computing Technologies,Chennai,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRM Institute of Science and Technology,Computing Technologies,Chennai,India","institution_ids":["https://openalex.org/I145286018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112058461","display_name":"R. Anita","orcid":null},"institutions":[{"id":"https://openalex.org/I145286018","display_name":"SRM Institute of Science and Technology","ror":"https://ror.org/050113w36","country_code":"IN","type":"education","lineage":["https://openalex.org/I145286018"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"R Anita","raw_affiliation_strings":["SRM Institute of Science and Technology,Computing Technologies,Chennai,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRM Institute of Science and Technology,Computing Technologies,Chennai,India","institution_ids":["https://openalex.org/I145286018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057393767","display_name":"J. D. Dorathi Jayaseeli","orcid":null},"institutions":[{"id":"https://openalex.org/I145286018","display_name":"SRM Institute of Science and Technology","ror":"https://ror.org/050113w36","country_code":"IN","type":"education","lineage":["https://openalex.org/I145286018"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"J D Dorathi Jayaseeli","raw_affiliation_strings":["SRM Institute of Science and Technology,Computing Technologies,Chennai,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRM Institute of Science and Technology,Computing Technologies,Chennai,India","institution_ids":["https://openalex.org/I145286018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082694737","display_name":"Sourabh Tiwari","orcid":"https://orcid.org/0000-0001-7641-2149"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sourabh Tiwari","raw_affiliation_strings":["Samsung R&D Institute,Voice Intelligence Group,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute,Voice Intelligence Group,Bangalore,India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063903476","display_name":"Rashmi T Shankarappa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rashmi T Shankarappa","raw_affiliation_strings":["Samsung R&D Institute,Voice Intelligence Group,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute,Voice Intelligence Group,Bangalore,India","institution_ids":["https://openalex.org/I4210139030"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16489921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9157000184059143,"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":0.9157000184059143,"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/griffin","display_name":"Griffin","score":0.8874070048332214},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7121797800064087},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6270260810852051},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5908714532852173},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.531541109085083},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4902415871620178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39898717403411865},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3658055067062378}],"concepts":[{"id":"https://openalex.org/C2775969163","wikidata":"https://www.wikidata.org/wiki/Q130223","display_name":"Griffin","level":2,"score":0.8874070048332214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7121797800064087},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6270260810852051},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5908714532852173},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.531541109085083},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4902415871620178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39898717403411865},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3658055067062378},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccnt61001.2024.10725517","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt61001.2024.10725517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT)","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":23,"referenced_works":["https://openalex.org/W2032062380","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2903594978","https://openalex.org/W2915977493","https://openalex.org/W2963779652","https://openalex.org/W2972495969","https://openalex.org/W3004753145","https://openalex.org/W3006211372","https://openalex.org/W3094211490","https://openalex.org/W3126424148","https://openalex.org/W3142316150","https://openalex.org/W3200318528","https://openalex.org/W3209552243","https://openalex.org/W4206712611","https://openalex.org/W4252337780","https://openalex.org/W4287848452","https://openalex.org/W6679434410","https://openalex.org/W6728610325","https://openalex.org/W6746700228","https://openalex.org/W6775587661","https://openalex.org/W6783957269","https://openalex.org/W6810419249"],"related_works":["https://openalex.org/W4245846742","https://openalex.org/W588680182","https://openalex.org/W2093304180","https://openalex.org/W2276557871","https://openalex.org/W3024933229","https://openalex.org/W145413986","https://openalex.org/W2414931473","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W123774389"],"abstract_inverted_index":{"At":[0],"present,":[1],"speech-to-speech":[2,55],"translator":[3,56],"systems":[4],"often":[5],"involve":[6],"multiple":[7],"intermediary":[8],"steps,":[9],"such":[10],"as":[11],"automatic":[12],"speech":[13,155],"recognition":[14],"(ASR),":[15],"text-to-text":[16],"machine":[17],"translation":[18,133],"(MT),":[19],"and":[20,30,69,171],"text-to-speech":[21],"generation":[22,156],"(TTS),":[23],"leading":[24],"to":[25,33,143],"latency":[26],"in":[27,85,147],"response":[28],"time":[29,130],"error":[31],"propagation":[32],"later":[34],"stages.":[35],"Furthermore,":[36],"they":[37],"face":[38],"challenges":[39],"when":[40],"dealing":[41],"with":[42,87],"languages":[43],"lacking":[44],"text":[45,64],"representation.":[46],"This":[47],"paper":[48],"examines":[49],"the":[50,60,72,141,158,163],"feasibility":[51],"of":[52,62,100,109,117,122,165],"a":[53,88,98,106,173],"direct":[54],"model":[57,94,104],"trained":[58],"without":[59],"use":[61],"intermediate":[63],"representations":[65],"during":[66],"both":[67],"training":[68,96],"inference.":[70],"Employing":[71],"Librosa":[73],"library":[74],"for":[75,95,132,168,176],"feature":[76],"extraction,":[77],"our":[78,166],"approach":[79,167],"uses":[80],"Mel-frequency":[81],"cepstral":[82],"coefficients":[83],"(MFCCs)":[84],"conjunction":[86],"sequence-to-sequence":[89],"Recurrent":[90],"Neural":[91],"Network":[92],"(RNN)":[93],"on":[97],"dataset":[99],"German-to-English":[101],"audio.":[102],"Our":[103,151],"achieved":[105],"BLEU":[107],"score":[108,121],"23.5,":[110],"demonstrating":[111],"competitive":[112],"performance.":[113],"The":[114,128],"Perceptual":[115],"Evaluation":[116],"Speech":[118],"Quality":[119],"(PESQ)":[120],"2.9":[123],"reveals":[124],"high-quality":[125],"generated":[126],"speech.":[127],"average":[129],"delay":[131],"is":[134],"${1.":[135],"5}$":[136],"seconds,":[137],"significantly":[138],"lower":[139],"than":[140],"2.5":[142],"3":[144],"seconds":[145],"observed":[146],"traditional":[148],"cascade":[149],"models.":[150],"experiments,":[152],"including":[153],"noise-free":[154],"using":[157],"Griffin":[159],"Lim":[160],"algorithm,":[161],"underline":[162],"potential":[164],"real-time":[169],"applications":[170],"lay":[172],"promising":[174],"foundation":[175],"future":[177],"research.":[178]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}