{"id":"https://openalex.org/W4410341529","doi":"https://doi.org/10.1109/ncc63735.2025.10983860","title":"Development of Resource Efficient Direct Speech to Speech Translation System using Transformer, Reformer, and Linformer","display_name":"Development of Resource Efficient Direct Speech to Speech Translation System using Transformer, Reformer, and Linformer","publication_year":2025,"publication_date":"2025-03-06","ids":{"openalex":"https://openalex.org/W4410341529","doi":"https://doi.org/10.1109/ncc63735.2025.10983860"},"language":"en","primary_location":{"id":"doi:10.1109/ncc63735.2025.10983860","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc63735.2025.10983860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 National Conference on Communications (NCC)","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, Electronics and Communication Engineering,Dharwad,India,580011"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Dharwad,Department of Electrical, Electronics and Communication 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, Electronics and Communication Engineering,Dharwad,India,580011"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Dharwad,Department of Electrical, Electronics and Communication 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":0.06328328,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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/T12031","display_name":"Speech and dialogue systems","score":0.9937000274658203,"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/transformer","display_name":"Transformer","score":0.6881498098373413},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6811389923095703},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5991755127906799},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.5980198979377747},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4731368124485016},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4524959921836853},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.29919275641441345},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.17756089568138123},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16639065742492676},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.15081650018692017}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6881498098373413},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6811389923095703},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5991755127906799},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.5980198979377747},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4731368124485016},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4524959921836853},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29919275641441345},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.17756089568138123},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16639065742492676},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.15081650018692017}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ncc63735.2025.10983860","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc63735.2025.10983860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 National Conference on Communications (NCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5099999904632568,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1538131130","https://openalex.org/W1583837637","https://openalex.org/W2903739847","https://openalex.org/W2963532001","https://openalex.org/W2964243274","https://openalex.org/W2972495969","https://openalex.org/W2990138404","https://openalex.org/W3033529678","https://openalex.org/W3142316150","https://openalex.org/W3180374548","https://openalex.org/W4221158946","https://openalex.org/W4285135638","https://openalex.org/W4293363567","https://openalex.org/W4295838474","https://openalex.org/W4385245566","https://openalex.org/W4392903062","https://openalex.org/W6741529945","https://openalex.org/W6771626834","https://openalex.org/W6777694618","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6810354702","https://openalex.org/W6841035593"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W2903810591","https://openalex.org/W2963499882","https://openalex.org/W3026554633","https://openalex.org/W2888520903","https://openalex.org/W2890256614","https://openalex.org/W3098873988","https://openalex.org/W2949454572","https://openalex.org/W3066373881"],"abstract_inverted_index":{"Direct":[0],"speech":[1,3,10],"to":[2,7,70,88],"translation":[4,114],"(DS2ST)":[5],"refers":[6],"directly":[8],"translating":[9],"from":[11],"one":[12],"language":[13,16],"into":[14],"another":[15],"without":[17],"relying":[18],"on":[19,53],"the":[20,35,84,89,98,110],"written":[21],"form.":[22],"Developing":[23],"such":[24,65],"systems":[25],"requires":[26],"a":[27,55],"significant":[28],"amount":[29],"of":[30,100,113,116],"parallel":[31],"data,":[32],"which":[33],"increases":[34],"demand":[36],"for":[37],"resources":[38],"like":[39],"GPU":[40],"memory":[41,60],"and":[42,61,68,106],"training":[43,81],"time,":[44],"consequently":[45],"raising":[46],"costs.":[47],"In":[48],"this":[49],"work,":[50],"we":[51],"focus":[52],"developing":[54],"DS2ST":[56],"system":[57],"using":[58],"more":[59],"time-efficient":[62],"transformer":[63],"architectures":[64],"as":[66],"Reformer":[67,79],"Linformer":[69,93],"address":[71],"these":[72],"challenges.":[73],"A":[74],"comparative":[75],"analysis":[76],"shows":[77],"that":[78],"accelerates":[80],"by$1.4\\times$and":[82],"reduces":[83,97],"complexity":[85],"from$\\mathrm{O}(n^{2})$to$\\mathrm{O}(n\\log":[86],"n)$compared":[87],"standard":[90],"Transformer.":[91],"Similarly,":[92],"speeds":[94],"up":[95],"by$1.7\\times$and":[96],"complex-ity":[99],"self-attention":[101],"from$\\mathrm{O}({n}^{2":[102],"})$to$\\mathrm{O}(n)$in":[103],"both":[104],"time":[105],"space":[107],"while":[108],"maintaining":[109],"same":[111],"level":[112],"accuracy":[115],"16.46":[117],"BLEU":[118],"score.":[119]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}