{"id":"https://openalex.org/W4416099404","doi":"https://doi.org/10.1142/s1469026825500129","title":"FPGA-Deployable PCNN-Based Neural Network Implementation for Real-Time Speech Recognition","display_name":"FPGA-Deployable PCNN-Based Neural Network Implementation for Real-Time Speech Recognition","publication_year":2025,"publication_date":"2025-11-11","ids":{"openalex":"https://openalex.org/W4416099404","doi":"https://doi.org/10.1142/s1469026825500129"},"language":"en","primary_location":{"id":"doi:10.1142/s1469026825500129","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1469026825500129","pdf_url":null,"source":{"id":"https://openalex.org/S206936884","display_name":"International Journal of Computational Intelligence and Applications","issn_l":"1469-0268","issn":["1469-0268","1757-5885"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Intelligence and Applications","raw_type":"journal-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/A5106943769","display_name":"H. Zhu","orcid":"https://orcid.org/0009-0000-5668-3021"},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hui-Sheng Zhu","raw_affiliation_strings":["National Cultural Industry Research, Central China Normal University, Wuhan, Hubei 430079, P. R. China"],"raw_orcid":"https://orcid.org/0009-0000-5668-3021","affiliations":[{"raw_affiliation_string":"National Cultural Industry Research, Central China Normal University, Wuhan, Hubei 430079, P. R. China","institution_ids":["https://openalex.org/I40963666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5106943769"],"corresponding_institution_ids":["https://openalex.org/I40963666"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16655724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"01","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":0.48030000925064087,"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":0.48030000925064087,"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":0.2736000120639801,"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.039799999445676804,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.656000018119812},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5788999795913696},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.5576000213623047},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5216000080108643},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4925000071525574},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.48590001463890076},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4674000144004822},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46380001306533813},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42809998989105225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8881999850273132},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.656000018119812},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5788999795913696},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.5576000213623047},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5386999845504761},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5216000080108643},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4925000071525574},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.48590001463890076},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4674000144004822},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46380001306533813},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42809998989105225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4221999943256378},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4180000126361847},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29429998993873596},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2556000053882599},{"id":"https://openalex.org/C20766975","wikidata":"https://www.wikidata.org/wiki/Q7390","display_name":"Human voice","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s1469026825500129","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1469026825500129","pdf_url":null,"source":{"id":"https://openalex.org/S206936884","display_name":"International Journal of Computational Intelligence and Applications","issn_l":"1469-0268","issn":["1469-0268","1757-5885"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Intelligence and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1790748249","https://openalex.org/W1982746914","https://openalex.org/W2337292434","https://openalex.org/W2792351646","https://openalex.org/W2899384503","https://openalex.org/W2923073871","https://openalex.org/W2923260971","https://openalex.org/W2944216546","https://openalex.org/W2950448225","https://openalex.org/W2994067526","https://openalex.org/W3000215093","https://openalex.org/W3011475824","https://openalex.org/W3101080767","https://openalex.org/W3119931181","https://openalex.org/W3130150650","https://openalex.org/W3148398210","https://openalex.org/W3157990190","https://openalex.org/W3198968036","https://openalex.org/W4285121050","https://openalex.org/W4292581907","https://openalex.org/W4319297957","https://openalex.org/W4361011475","https://openalex.org/W4378594122","https://openalex.org/W4387643472","https://openalex.org/W4391127431","https://openalex.org/W4391127493","https://openalex.org/W4391127838","https://openalex.org/W4391127843","https://openalex.org/W4391127953","https://openalex.org/W4395463271","https://openalex.org/W4399502854","https://openalex.org/W4400900126","https://openalex.org/W4401670088","https://openalex.org/W4402804228","https://openalex.org/W4406373150","https://openalex.org/W4408260779","https://openalex.org/W4408946550"],"related_works":[],"abstract_inverted_index":{"This":[0,189],"paper":[1],"describes":[2],"a":[3,61,68,94,138,192,210],"neural":[4,19,63,69,95],"network":[5,64,96],"algorithm-based":[6],"FPGA-implemented":[7],"real-time":[8,31,120,250],"human":[9,86,99],"speech":[10,17,52,87,100,146,251],"denoising":[11,33,122],"approach.":[12],"In":[13,42],"the":[14,113,127,155,234],"realm":[15],"of":[16,129,154,160,212,243],"processing,":[18],"networks":[20],"have":[21],"become":[22],"increasingly":[23],"popular":[24],"as":[25],"artificial":[26],"intelligence":[27],"technology":[28],"advances.":[29],"Applying":[30],"voice":[32],"to":[34,44,57,72,84,132,143,227,248],"embedded":[35,149],"systems":[36],"with":[37,54],"limited":[38],"resources":[39],"remains":[40],"challenging.":[41],"addition":[43],"denoising,":[45],"this":[46,74],"work":[47],"explores":[48],"feature":[49],"extraction":[50],"for":[51,98,105,199,202,206],"recognition,":[53],"particular":[55],"attention":[56],"spectrogram-based":[58],"methods":[59],"using":[60,82],"pulse-coupled":[62],"(PCNN).":[65],"We":[66,92],"suggest":[67],"network-based":[70],"technique":[71],"address":[73],"issue,":[75],"and":[76,102,121,136,169,181,204,216],"we":[77],"put":[78],"it":[79,104,246],"into":[80],"practice":[81],"FPGAs":[83],"handle":[85],"noise":[88],"in":[89,119,148,167,172,236],"real":[90],"time.":[91],"refined":[93],"architecture":[97],"inputs":[101],"developed":[103],"FPGA":[106,223],"hardware":[107],"acceleration.":[108],"The":[109,151,222],"experimental":[110],"findings":[111],"demonstrate":[112],"tremendous":[114],"advancements":[115],"our":[116],"method":[117],"makes":[118],"effect,":[123],"while":[124],"also":[125],"showing":[126],"potential":[128],"PCNN":[130],"features":[131],"improve":[133],"recognition":[134],"stability":[135],"offer":[137],"fresh":[139],"perspective":[140],"on":[141],"how":[142],"effectively":[144],"apply":[145],"processing":[147],"systems.":[150],"overall":[152],"improvement":[153],"system":[156],"was":[157],"an":[158,175],"average":[159],"[Formula:":[161,164,177,182,229],"see":[162,165,178,183,214,218,230],"text]":[163,179,184,231],"text]dB":[166],"SNR,":[168],"when":[170],"evaluated":[171],"noisy":[173],"conditions,":[174],"additional":[176],"PESQ":[180],"STOI":[185],"could":[186],"be":[187,228],"gained.":[188],"implementation":[190],"(on":[191],"Xilinx":[193],"Zynq-7020":[194],"FPGA)":[195],"consumed":[196],"approximately":[197],"21%":[198],"LUTs,":[200],"18%":[201],"DSPs,":[203],"25%":[205],"BRAM.":[207],"It":[208],"had":[209],"latency":[211],"1.8[Formula:":[213],"text]ms":[215],"1.2[Formula:":[217],"text]W":[219],"power":[220],"consumption.":[221],"design":[224],"turned":[225],"out":[226],"faster":[232],"than":[233],"CPU":[235],"standard":[237],"configurations,":[238],"which":[239],"saves":[240],"over":[241],"70%":[242],"energy,":[244],"making":[245],"possible":[247],"implement":[249],"denoising.":[252]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-11-11T00:00:00"}