{"id":"https://openalex.org/W4224920132","doi":"https://doi.org/10.1109/icassp43922.2022.9747499","title":"Speech Recognition Using Biologically-Inspired Neural Networks","display_name":"Speech Recognition Using Biologically-Inspired Neural Networks","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224920132","doi":"https://doi.org/10.1109/icassp43922.2022.9747499"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747499","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5110692394","display_name":"Thomas Bohnstingl","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Thomas Bohnstingl","raw_affiliation_strings":["IBM Research,Zurich","IBM Research, Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Zurich","institution_ids":["https://openalex.org/I4210126328"]},{"raw_affiliation_string":"IBM Research, Zurich","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005609029","display_name":"Ayush Garg","orcid":"https://orcid.org/0000-0001-6402-8529"},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ayush Garg","raw_affiliation_strings":["IBM Research,Zurich","IBM Research, Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Zurich","institution_ids":["https://openalex.org/I4210126328"]},{"raw_affiliation_string":"IBM Research, Zurich","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072695145","display_name":"Stanis\u0142aw Wo\u017aniak","orcid":"https://orcid.org/0000-0001-7282-3792"},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Stanislaw Wozniak","raw_affiliation_strings":["IBM Research,Zurich","IBM Research, Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Zurich","institution_ids":["https://openalex.org/I4210126328"]},{"raw_affiliation_string":"IBM Research, Zurich","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Research AI,Yorktown Heights,USA","Yorktown Heights, IBM Research AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI,Yorktown Heights,USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"Yorktown Heights, IBM Research AI, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043271107","display_name":"Evangelos Eleftheriou","orcid":"https://orcid.org/0000-0002-3826-5931"},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Evangelos Eleftheriou","raw_affiliation_strings":["IBM Research,Zurich","IBM Research, Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Zurich","institution_ids":["https://openalex.org/I4210126328"]},{"raw_affiliation_string":"IBM Research, Zurich","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024779827","display_name":"Angeliki Pantazi","orcid":"https://orcid.org/0000-0003-4720-4038"},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Angeliki Pantazi","raw_affiliation_strings":["IBM Research,Zurich","IBM Research, Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Zurich","institution_ids":["https://openalex.org/I4210126328"]},{"raw_affiliation_string":"IBM Research, Zurich","institution_ids":["https://openalex.org/I4210126328"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7267,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.69780016,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6992","last_page":"6996"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987000226974487,"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":0.9983999729156494,"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":0.7390265464782715},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5405994057655334},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5229321718215942},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4742894768714905}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390265464782715},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5405994057655334},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5229321718215942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4742894768714905}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747499","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":35,"referenced_works":["https://openalex.org/W61757119","https://openalex.org/W274985342","https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W1987011838","https://openalex.org/W2026698108","https://openalex.org/W2048812218","https://openalex.org/W2115831804","https://openalex.org/W2168311770","https://openalex.org/W2327501763","https://openalex.org/W2432549741","https://openalex.org/W2503929286","https://openalex.org/W2519224033","https://openalex.org/W2896339047","https://openalex.org/W2908510526","https://openalex.org/W2945427955","https://openalex.org/W2962760690","https://openalex.org/W2964539095","https://openalex.org/W2973122799","https://openalex.org/W3011339933","https://openalex.org/W3016167541","https://openalex.org/W3035400263","https://openalex.org/W3097777922","https://openalex.org/W3134388707","https://openalex.org/W3141464856","https://openalex.org/W3163300396","https://openalex.org/W3197479040","https://openalex.org/W4298355310","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6749922295","https://openalex.org/W6756319913","https://openalex.org/W6757817989","https://openalex.org/W6763194437","https://openalex.org/W6783954938"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"recognition":[2],"systems":[3],"(ASR),":[4],"such":[5,123],"as":[6],"the":[7,31,35,39,42,66,82,103,106,113,119,132],"recurrent":[8],"neural":[9,85,99],"network":[10],"transducer":[11],"(RNN-T),":[12],"have":[13],"reached":[14],"close":[15],"to":[16,131],"human-like":[17],"performance":[18,128],"and":[19,55,74,86,105,109,143],"are":[20],"deployed":[21],"in":[22,45,51],"commercial":[23],"applications.":[24,60],"However,":[25],"their":[26,76],"core":[27],"operations":[28],"depart":[29],"from":[30,81],"powerful":[32],"biological":[33],"counterpart,":[34],"human":[36],"brain.":[37],"On":[38],"other":[40],"hand,":[41],"current":[43],"developments":[44],"biologically-inspired":[46],"ASR":[47],"models":[48,70],"lag":[49],"behind":[50],"terms":[52],"of":[53,68],"accuracy":[54],"focus":[56],"primarily":[57],"on":[58],"small-scale":[59],"In":[61,89],"this":[62],"work,":[63],"we":[64,91],"revisit":[65],"incorporation":[67],"biologically-plausible":[69],"into":[71,112],"deep":[72,94],"learning":[73,95],"enhance":[75],"capabilities,":[77],"by":[78,97],"taking":[79],"inspiration":[80],"brain\u2019s":[83],"diverse":[84],"synaptic":[87],"dynamics.":[88],"particular,":[90],"propose":[92],"novel":[93],"units":[96],"introducing":[98],"connectivity":[100],"concepts":[101],"emulating":[102],"axo-somatic":[104],"axo-axonic":[107],"synapses":[108],"integrate":[110],"them":[111],"RNN-T":[114],"architecture.":[115],"We":[116],"demonstrate":[117],"for":[118],"first":[120],"time":[121],"that":[122],"a":[124,138,144],"model":[125],"can":[126],"yield":[127],"levels":[129],"competitive":[130],"state-of-the-art.":[133],"Moreover,":[134],"our":[135],"implementation":[136],"has":[137],"significantly":[139],"reduced":[140],"computational":[141],"cost":[142],"lower":[145],"latency.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
