{"id":"https://openalex.org/W4375869285","doi":"https://doi.org/10.1109/icassp49357.2023.10096271","title":"Diagonal State Space Augmented Transformers for Speech Recognition","display_name":"Diagonal State Space Augmented Transformers for Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869285","doi":"https://doi.org/10.1109/icassp49357.2023.10096271"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096271","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/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":true,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Research AI,Yorktown Heights,USA","IBM Research AI, Yorktown Heights, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI,Yorktown Heights,USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022734062","display_name":"Ankit Gupta","orcid":"https://orcid.org/0009-0002-0406-0716"},"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":"Ankit Gupta","raw_affiliation_strings":["IBM Research AI,Yorktown Heights,USA","IBM Research AI, Yorktown Heights, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI,Yorktown Heights,USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102014291","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0003-4865-1307"},"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":"Xiaodong Cui","raw_affiliation_strings":["IBM Research AI,Yorktown Heights,USA","IBM Research AI, Yorktown Heights, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI,Yorktown Heights,USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079994647"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":1.7483,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87305915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"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/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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976999759674072,"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":0.9958999752998352,"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/transformer","display_name":"Transformer","score":0.5521902441978455},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.545153021812439},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5316750407218933},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.5260467529296875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43880727887153625},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35805273056030273},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27176064252853394},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.15825730562210083},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09119865298271179}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5521902441978455},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.545153021812439},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5316750407218933},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.5260467529296875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43880727887153625},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35805273056030273},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27176064252853394},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.15825730562210083},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09119865298271179},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096271","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":0.7900000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W2103584254","https://openalex.org/W2407080277","https://openalex.org/W2936774411","https://openalex.org/W2937780860","https://openalex.org/W2964110616","https://openalex.org/W2972974544","https://openalex.org/W3008037978","https://openalex.org/W3015190365","https://openalex.org/W3064840847","https://openalex.org/W3097777922","https://openalex.org/W3101171795","https://openalex.org/W3152519008","https://openalex.org/W3157428800","https://openalex.org/W3162090017","https://openalex.org/W3163300396","https://openalex.org/W3163793923","https://openalex.org/W3197813307","https://openalex.org/W3198654230","https://openalex.org/W3204696009","https://openalex.org/W3207629995","https://openalex.org/W3209374680","https://openalex.org/W3211278025","https://openalex.org/W4221145950","https://openalex.org/W4221151563","https://openalex.org/W4221151615","https://openalex.org/W4225307083","https://openalex.org/W4283461773","https://openalex.org/W4283734749","https://openalex.org/W4283768831","https://openalex.org/W4296069265","https://openalex.org/W4320006236","https://openalex.org/W6631362777","https://openalex.org/W6782420349","https://openalex.org/W6793959113"],"related_works":["https://openalex.org/W2006251942","https://openalex.org/W2364741597","https://openalex.org/W1492103595","https://openalex.org/W1864774435","https://openalex.org/W946352265","https://openalex.org/W3020787026","https://openalex.org/W2334479858","https://openalex.org/W2799209613","https://openalex.org/W1971388572","https://openalex.org/W1507702947"],"abstract_inverted_index":{"We":[0,71],"improve":[1,139],"on":[2,85,124,136],"the":[3,9,44,54,65,68,125,130,140,146,167,174],"popular":[4],"conformer":[5,77],"architecture":[6],"by":[7,29,64,142],"replacing":[8],"depthwise":[10],"temporal":[11],"convolutions":[12],"with":[13,35,75],"diagonal":[14,37],"state":[15,38],"space":[16,49],"(DSS)":[17],"models.":[18],"DSS":[19,41,159],"is":[20,62],"a":[21,31,36,48,100,117],"recently":[22],"introduced":[23],"variant":[24],"of":[25,50,56,67,103,121,129],"linear":[26,32],"RNNs":[27],"obtained":[28],"discretizing":[30],"dynamical":[33],"system":[34],"transition":[39,69],"matrix.":[40,70],"layers":[42,160],"project":[43],"input":[45],"sequence":[46],"onto":[47],"orthogonal":[51],"polynomials":[52],"where":[53,166],"choice":[55],"basis":[57,164],"functions,":[58],"metric":[59],"and":[60,99,135],"support":[61],"controlled":[63],"eigenvalues":[66],"compare":[72],"neural":[73],"transducers":[74],"either":[76],"or":[78],"our":[79],"proposed":[80],"DSS-augmented":[81],"transformer":[82],"(DSSformer)":[83],"encoders":[84],"three":[86],"public":[87],"corpora:":[88],"Switchboard":[89,112],"English":[90],"conversational":[91],"telephone":[92],"speech":[93],"300":[94],"hours,":[95,98,114],"Switchboard+Fisher":[96],"2000":[97,132],"spoken":[101],"archive":[102],"holocaust":[104],"survivor":[105],"testimonials":[106],"called":[107],"MALACH":[108,137],"176":[109],"hours.":[110],"On":[111],"300/2000":[113],"we":[115,138,153],"reach":[116],"single":[118],"model":[119],"performance":[120],"8.9%/6.7%":[122],"WER":[123,141],"combined":[126],"test":[127],"set":[128],"Hub5":[131],"evaluation,":[133],"respectively,":[134],"7%":[143],"relative":[144],"over":[145],"previous":[147],"best":[148],"published":[149],"result.":[150],"In":[151],"addition,":[152],"present":[154],"empirical":[155],"evidence":[156],"suggesting":[157],"that":[158],"learn":[161],"damped":[162],"Fourier":[163],"functions":[165],"attenuation":[168],"coefficients":[169,176],"are":[170],"layer":[171],"specific":[172],"whereas":[173],"frequency":[175],"converge":[177],"to":[178],"almost":[179],"identical":[180],"linearly-spaced":[181],"values":[182],"across":[183],"all":[184],"layers.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}