{"id":"https://openalex.org/W3185921853","doi":"https://doi.org/10.1186/s13636-021-00217-4","title":"Performance vs. hardware requirements in state-of-the-art automatic speech recognition","display_name":"Performance vs. hardware requirements in state-of-the-art automatic speech recognition","publication_year":2021,"publication_date":"2021-07-21","ids":{"openalex":"https://openalex.org/W3185921853","doi":"https://doi.org/10.1186/s13636-021-00217-4","mag":"3185921853"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-021-00217-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00217-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-021-00217-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-021-00217-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101877302","display_name":"Alexandru-Lucian Georgescu","orcid":"https://orcid.org/0000-0003-2122-4997"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Alexandru-Lucian Georgescu","raw_affiliation_strings":["Speech and Dialogue Research Laboratory, University Politehnica of Bucharest, Bucharest, Romania"],"raw_orcid":"https://orcid.org/0000-0003-2122-4997","affiliations":[{"raw_affiliation_string":"Speech and Dialogue Research Laboratory, University Politehnica of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076669165","display_name":"Alessandro Pappalardo","orcid":"https://orcid.org/0000-0001-9386-5510"},"institutions":[{"id":"https://openalex.org/I4210101362","display_name":"Xilinx (Ireland)","ror":"https://ror.org/00pahkj72","country_code":"IE","type":"company","lineage":["https://openalex.org/I32923980","https://openalex.org/I4210101362"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Alessandro Pappalardo","raw_affiliation_strings":["Research Labs, Xilinx, Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Labs, Xilinx, Dublin, Ireland","institution_ids":["https://openalex.org/I4210101362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032257745","display_name":"Horia Cucu","orcid":"https://orcid.org/0000-0002-8711-3854"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Horia Cucu","raw_affiliation_strings":["Speech and Dialogue Research Laboratory, University Politehnica of Bucharest, Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Dialogue Research Laboratory, University Politehnica of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031107943","display_name":"Michaela Blott","orcid":"https://orcid.org/0000-0002-7833-4057"},"institutions":[{"id":"https://openalex.org/I4210101362","display_name":"Xilinx (Ireland)","ror":"https://ror.org/00pahkj72","country_code":"IE","type":"company","lineage":["https://openalex.org/I32923980","https://openalex.org/I4210101362"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Michaela Blott","raw_affiliation_strings":["Research Labs, Xilinx, Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Labs, Xilinx, Dublin, Ireland","institution_ids":["https://openalex.org/I4210101362"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":2.5188,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.91117382,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"2021","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"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/T11309","display_name":"Music and Audio Processing","score":0.9947999715805054,"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/computer-science","display_name":"Computer science","score":0.8904520273208618},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6874082684516907},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5025415420532227},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.49063268303871155},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.47657251358032227},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46358275413513184},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44826775789260864},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4394151568412781},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4262203872203827},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4154418706893921},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4102051854133606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.380026638507843},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.1466713845729828},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11719653010368347}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8904520273208618},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6874082684516907},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5025415420532227},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.49063268303871155},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.47657251358032227},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46358275413513184},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44826775789260864},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4394151568412781},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4262203872203827},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4154418706893921},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4102051854133606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.380026638507843},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.1466713845729828},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11719653010368347},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-021-00217-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00217-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-021-00217-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5791e9a5e49f4289b92701df43133aab","is_oa":true,"landing_page_url":"https://doaj.org/article/5791e9a5e49f4289b92701df43133aab","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2021, Iss 1, Pp 1-30 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-021-00217-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00217-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-021-00217-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7699999809265137,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G7688415803","display_name":null,"funder_award_id":"PN-III-P1-1","funder_id":"https://openalex.org/F4320323983","funder_display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii"},{"id":"https://openalex.org/G788691142","display_name":null,"funder_award_id":"PN-III-P1-1.2-PCCDI","funder_id":"https://openalex.org/F4320323983","funder_display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii"},{"id":"https://openalex.org/G900005651","display_name":null,"funder_award_id":"PN-III-P1-1.2-PCCDI-","funder_id":"https://openalex.org/F4320323983","funder_display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii"}],"funders":[{"id":"https://openalex.org/F4320314786","display_name":"Xilinx","ror":"https://ror.org/01rb7bk56"},{"id":"https://openalex.org/F4320323983","display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii","ror":"https://ror.org/01q7jq182"},{"id":"https://openalex.org/F4320336189","display_name":"Colegiul Consultativ pentru Cercetare-Dezvoltare \u015fi Inovare","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3185921853.pdf","grobid_xml":"https://content.openalex.org/works/W3185921853.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1991133427","https://openalex.org/W1995562189","https://openalex.org/W2024490156","https://openalex.org/W2086699924","https://openalex.org/W2103869314","https://openalex.org/W2107638917","https://openalex.org/W2117671523","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2148154194","https://openalex.org/W2150769028","https://openalex.org/W2158069733","https://openalex.org/W2160815625","https://openalex.org/W2166637769","https://openalex.org/W2169992508","https://openalex.org/W2171928131","https://openalex.org/W2184045248","https://openalex.org/W2293634267","https://openalex.org/W2327501763","https://openalex.org/W2402146185","https://openalex.org/W2514741789","https://openalex.org/W2529096783","https://openalex.org/W2562294437","https://openalex.org/W2585720638","https://openalex.org/W2618099328","https://openalex.org/W2627092829","https://openalex.org/W2766195687","https://openalex.org/W2799800213","https://openalex.org/W2802201485","https://openalex.org/W2888779557","https://openalex.org/W2888867175","https://openalex.org/W2889282842","https://openalex.org/W2891540872","https://openalex.org/W2911109671","https://openalex.org/W2931364255","https://openalex.org/W2940180244","https://openalex.org/W2951726497","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2963071736","https://openalex.org/W2963240019","https://openalex.org/W2963362078","https://openalex.org/W2963446712","https://openalex.org/W2963654251","https://openalex.org/W2963882470","https://openalex.org/W2964107261","https://openalex.org/W2964110616","https://openalex.org/W2964199361","https://openalex.org/W2964539095","https://openalex.org/W2972384088","https://openalex.org/W2972630480","https://openalex.org/W2973215447","https://openalex.org/W3004597053","https://openalex.org/W3015537910","https://openalex.org/W3045086295","https://openalex.org/W3168770049","https://openalex.org/W4233670287","https://openalex.org/W4255111198","https://openalex.org/W4285719527","https://openalex.org/W6629259071"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2744553356","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2188872161","https://openalex.org/W2961779879","https://openalex.org/W797688974","https://openalex.org/W2002978035"],"abstract_inverted_index":{"Abstract":[0],"The":[1,56,119],"last":[2],"decade":[3],"brought":[4],"significant":[5],"advances":[6],"in":[7,82,135],"automatic":[8],"speech":[9,29,110],"recognition":[10,111],"(ASR)":[11],"thanks":[12],"to":[13,38,62,86,91,130,156],"the":[14,44,74,106,114,122,137,146,153],"evolution":[15],"of":[16,73,148,160],"deep":[17,52],"learning":[18],"methods.":[19],"ASR":[20,63,76,117,125,165],"systems":[21],"evolved":[22],"from":[23],"pipeline-based":[24],"systems,":[25,41],"that":[26,42],"modeled":[27],"hand-crafted":[28],"features":[30],"with":[31],"probabilistic":[32],"frameworks":[33],"and":[34,94,112,127],"generated":[35],"phone":[36],"posteriors,":[37],"end-to-end":[39],"(E2E)":[40],"translate":[43],"raw":[45],"waveform":[46],"directly":[47],"into":[48,67],"words":[49],"using":[50],"one":[51],"neural":[53],"network":[54],"(DNN).":[55],"transcription":[57],"accuracy":[58],"greatly":[59],"increased,":[60],"leading":[61],"technology":[64],"being":[65],"integrated":[66],"many":[68],"commercial":[69],"applications.":[70],"However,":[71],"few":[72],"existing":[75],"technologies":[77],"are":[78],"suitable":[79],"for":[80,163],"integration":[81],"embedded":[83,143],"applications,":[84],"due":[85],"their":[87,142],"hard":[88],"constrains":[89],"related":[90],"computing":[92],"power":[93],"memory":[95],"usage.":[96],"This":[97],"overview":[98],"paper":[99],"serves":[100],"as":[101],"a":[102],"guided":[103],"tour":[104],"through":[105],"recent":[107],"literature":[108],"on":[109],"compares":[113],"most":[115],"popular":[116],"implementations.":[118],"comparison":[120],"emphasizes":[121],"trade-off":[123,161],"between":[124],"performance":[126],"hardware":[128],"requirements,":[129],"further":[131],"serve":[132],"decision":[133],"makers":[134],"choosing":[136],"system":[138],"which":[139],"fits":[140],"best":[141,147],"application.":[144],"To":[145],"our":[149],"knowledge,":[150],"this":[151,158],"is":[152],"first":[154],"study":[155],"provide":[157],"kind":[159],"analysis":[162],"state-of-the-art":[164],"systems.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}