{"id":"https://openalex.org/W4375869094","doi":"https://doi.org/10.1109/icassp49357.2023.10096248","title":"Neural Architecture of Speech","display_name":"Neural Architecture of Speech","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869094","doi":"https://doi.org/10.1109/icassp49357.2023.10096248"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5029606497","display_name":"Subba Reddy Oota","orcid":"https://orcid.org/0000-0002-5975-622X"},"institutions":[{"id":"https://openalex.org/I4210131512","display_name":"Centre Inria de l'universit\u00e9 de Bordeaux","ror":"https://ror.org/03tjcj052","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210131512"]},{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["FR","IN"],"is_corresponding":false,"raw_author_name":"Subba Reddy Oota","raw_affiliation_strings":["Inria Bordeaux,France","IIIT Hyderabad","Inria Bordeaux, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria Bordeaux,France","institution_ids":[]},{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"Inria Bordeaux, France","institution_ids":["https://openalex.org/I4210131512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032698955","display_name":"Khushbu Pahwa","orcid":"https://orcid.org/0009-0009-6976-6120"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khushbu Pahwa","raw_affiliation_strings":["University of California, LA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, LA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062052248","display_name":"Mounika Marreddy","orcid":"https://orcid.org/0000-0003-1184-640X"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mounika Marreddy","raw_affiliation_strings":["IIIT Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101454729","display_name":"Manish Gupta","orcid":"https://orcid.org/0000-0003-0848-6132"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["GB","IN"],"is_corresponding":false,"raw_author_name":"Manish Gupta","raw_affiliation_strings":["IIIT Hyderabad","Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049423985","display_name":"Raju S. Bapi","orcid":"https://orcid.org/0000-0003-2204-0890"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Bapi S. Raju","raw_affiliation_strings":["IIIT Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2933,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80233998,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"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/T11309","display_name":"Music and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7460415959358215},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5475094318389893},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5294613242149353},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5238418579101562},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5080101490020752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4749467670917511},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46425893902778625},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4608328938484192},{"id":"https://openalex.org/keywords/functional-magnetic-resonance-imaging","display_name":"Functional magnetic resonance imaging","score":0.4477882981300354},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.4287334084510803},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34693944454193115},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.1514776051044464},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.138776034116745},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.09070849418640137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7460415959358215},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5475094318389893},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5294613242149353},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5238418579101562},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5080101490020752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4749467670917511},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46425893902778625},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4608328938484192},{"id":"https://openalex.org/C2779226451","wikidata":"https://www.wikidata.org/wiki/Q903809","display_name":"Functional magnetic resonance imaging","level":2,"score":0.4477882981300354},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.4287334084510803},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34693944454193115},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.1514776051044464},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.138776034116745},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.09070849418640137},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1992570774","https://openalex.org/W2344975321","https://openalex.org/W2526050071","https://openalex.org/W2892147425","https://openalex.org/W2945310593","https://openalex.org/W2947012833","https://openalex.org/W2953945416","https://openalex.org/W2970648593","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2982223350","https://openalex.org/W2983144399","https://openalex.org/W2997066978","https://openalex.org/W3015213852","https://openalex.org/W3015265920","https://openalex.org/W3016181583","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3085600465","https://openalex.org/W3097286738","https://openalex.org/W3101022551","https://openalex.org/W3103949942","https://openalex.org/W3112034174","https://openalex.org/W3148040514","https://openalex.org/W3167207712","https://openalex.org/W3197411683","https://openalex.org/W3197580070","https://openalex.org/W3198858531","https://openalex.org/W3201143670","https://openalex.org/W3203140070","https://openalex.org/W3206532275","https://openalex.org/W3206626273","https://openalex.org/W3206996142","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221145109","https://openalex.org/W4224821750","https://openalex.org/W4224927631","https://openalex.org/W4226399507","https://openalex.org/W4281765823","https://openalex.org/W4287854368","https://openalex.org/W4297841853","https://openalex.org/W4317536043","https://openalex.org/W4320086272","https://openalex.org/W6754825039","https://openalex.org/W6763027002","https://openalex.org/W6765524274","https://openalex.org/W6767096107","https://openalex.org/W6769196770","https://openalex.org/W6777232839","https://openalex.org/W6780218876","https://openalex.org/W6783041029","https://openalex.org/W6784776607","https://openalex.org/W6786669483","https://openalex.org/W6788335241","https://openalex.org/W6804298400","https://openalex.org/W6810007534","https://openalex.org/W6838662218","https://openalex.org/W6846678071","https://openalex.org/W6849003372"],"related_works":["https://openalex.org/W2372020181","https://openalex.org/W2156531654","https://openalex.org/W1581723585","https://openalex.org/W4378714697","https://openalex.org/W2294330161","https://openalex.org/W2253069048","https://openalex.org/W2804553224","https://openalex.org/W140709781","https://openalex.org/W3214340375","https://openalex.org/W1510159504"],"abstract_inverted_index":{"A":[0],"vast":[1],"literature":[2],"on":[3,29,39,80,92],"brain":[4,16,30,40,108,147,184],"encoding":[5,31,41],"has":[6],"effectively":[7],"harnessed":[8],"deep":[9,81],"neural":[10,99],"network":[11],"models":[12,53,67,83,101,118,138,168],"for":[13,32,42,54,84,149],"accurately":[14],"predicting":[15],"activations":[17],"from":[18],"visual":[19],"or":[20],"text":[21,48],"stimuli.":[22,34],"Unfortunately,":[23],"there":[24],"is":[25],"not":[26],"much":[27],"work":[28],"speech":[33,43,46,64,73,95,100,116,141],"The":[35],"few":[36],"existing":[37],"studies":[38],"stimuli":[44,142],"transcribe":[45],"to":[47,102,134],"and":[49,106,131,143,166,182],"then":[50],"leverage":[51],"text-only":[52],"encoding,":[55],"thereby":[56],"ignoring":[57],"audio":[58],"signals":[59],"completely.":[60],"However,":[61],"recently":[62],"several":[63],"representation":[65,117],"learning":[66,82],"have":[68],"revolutionized":[69],"the":[70,77,140,150,177],"field":[71],"of":[72],"processing.":[74],"Inspired":[75],"by":[76,97],"recent":[78],"progress":[79],"speech,":[85],"we":[86,113],"present":[87],"a":[88],"first":[89],"systematic":[90],"study":[91,135],"understanding":[93],"human":[94,146],"processing":[96],"probing":[98],"predict":[103],"both":[104,163,180],"language":[105,181],"auditory":[107,183],"region":[109],"activations.":[110],"In":[111],"particular,":[112],"investigate":[114],"30":[115],"grouped":[119],"into":[120],"four":[121],"categories:":[122],"(i)":[123],"traditional":[124],"feature":[125],"engineering,":[126],"(ii)":[127],"generative,":[128],"(iii)":[129],"predictive,":[130],"(iv)":[132],"contrastive,":[133],"how":[136],"these":[137],"encode":[139],"align":[144],"with":[145,179],"activity":[148],"Moth":[151],"Radio":[152],"Hour":[153],"fMRI":[154],"(functional":[155],"magnetic":[156],"resonance":[157],"imaging)":[158],"dataset.":[159],"We":[160,190],"find":[161],"that":[162],"contrastive":[164],"(Wav2Vec2.0)":[165],"predictive":[167],"(HuBERT,":[169],"Data2Vec)":[170],"are":[171],"very":[172],"accurate.":[173],"Specifically,":[174],"Data2Vec":[175],"aligns":[176],"best":[178],"regions":[185],"among":[186],"all":[187],"investigated":[188],"models.":[189],"make":[191],"our":[192],"code":[193],"publicly":[194],"available":[195],"<sup":[196],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[197],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[198],".":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}