{"id":"https://openalex.org/W4392910298","doi":"https://doi.org/10.1109/icassp48485.2024.10445950","title":"Augmenting Conformers With Structured State-Space Sequence Models For Online Speech Recognition","display_name":"Augmenting Conformers With Structured State-Space Sequence Models For Online Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910298","doi":"https://doi.org/10.1109/icassp48485.2024.10445950"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5044483824","display_name":"Haozhe Shan","orcid":"https://orcid.org/0000-0002-1168-4861"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Haozhe Shan","raw_affiliation_strings":["Harvard University"],"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025386668","display_name":"Albert Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Albert Gu","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong Meng","raw_affiliation_strings":["Google LLC"],"affiliations":[{"raw_affiliation_string":"Google LLC","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101432591","display_name":"Weiran Wang","orcid":"https://orcid.org/0009-0000-0843-707X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiran Wang","raw_affiliation_strings":["Google LLC"],"affiliations":[{"raw_affiliation_string":"Google LLC","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031842812","display_name":"Krzysztof Choroma\u0144ski","orcid":"https://orcid.org/0000-0003-3626-414X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krzysztof Choromanski","raw_affiliation_strings":["Google LLC"],"affiliations":[{"raw_affiliation_string":"Google LLC","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara Sainath","raw_affiliation_strings":["Google LLC"],"affiliations":[{"raw_affiliation_string":"Google LLC","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5044483824"],"corresponding_institution_ids":["https://openalex.org/I2801851002"],"apc_list":null,"apc_paid":null,"fwci":1.1304,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74813942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"12221","last_page":"12225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9891999959945679,"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/T10860","display_name":"Speech and Audio Processing","score":0.9891999959945679,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9768999814987183,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9613000154495239,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7064432501792908},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6188404560089111},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6152921915054321},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4413038194179535},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4275939464569092},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41893044114112854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41056588292121887},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1313742995262146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7064432501792908},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6188404560089111},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6152921915054321},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4413038194179535},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4275939464569092},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41893044114112854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41056588292121887},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1313742995262146},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2064675550","https://openalex.org/W2112796928","https://openalex.org/W2144499799","https://openalex.org/W2160815625","https://openalex.org/W2754232744","https://openalex.org/W2936774411","https://openalex.org/W2964110616","https://openalex.org/W3097777922","https://openalex.org/W3209374680","https://openalex.org/W4313442864","https://openalex.org/W4321593177","https://openalex.org/W4372260519","https://openalex.org/W4375869285","https://openalex.org/W4385822815","https://openalex.org/W6739901393","https://openalex.org/W6744720862","https://openalex.org/W6780218876","https://openalex.org/W6802912272","https://openalex.org/W6803444062","https://openalex.org/W6809915218","https://openalex.org/W6839026989","https://openalex.org/W6839235732","https://openalex.org/W6841205203","https://openalex.org/W6843425716","https://openalex.org/W6848875551","https://openalex.org/W6850033884"],"related_works":["https://openalex.org/W2112284452","https://openalex.org/W3085798047","https://openalex.org/W2374269412","https://openalex.org/W371123309","https://openalex.org/W380379685","https://openalex.org/W2085500676","https://openalex.org/W2186272223","https://openalex.org/W2012817876","https://openalex.org/W2365096715","https://openalex.org/W2062838854"],"abstract_inverted_index":{"Online":[0],"speech":[1],"recognition,":[2],"where":[3],"the":[4,10,79],"model":[5,104],"only":[6],"accesses":[7],"context":[8],"to":[9,60,84,99],"left,":[11],"is":[12,83],"an":[13],"important":[14],"and":[15,66],"challenging":[16],"use":[17],"case":[18],"for":[19,30],"ASR":[20,32],"systems.":[21],"In":[22],"this":[23],"work,":[24],"we":[25],"investigate":[26],"augmenting":[27],"neural":[28],"encoders":[29],"online":[31],"by":[33],"incorporating":[34],"structured":[35],"state-space":[36],"sequence":[37],"models":[38,43,65],"(S4),":[39],"a":[40,46,86,94],"family":[41],"of":[42,49,63,107],"that":[44,71,78],"provide":[45],"parameter-efficient":[47],"way":[48],"accessing":[50],"arbitrarily":[51],"long":[52],"left":[53],"context.":[54],"We":[55,76],"performed":[56],"systematic":[57],"ablation":[58],"studies":[59],"compare":[61],"variants":[62],"S4":[64,88],"propose":[67],"two":[68],"novel":[69],"approaches":[70],"combine":[72],"them":[73,98],"with":[74,93,116],"convolutions.":[75],"found":[77],"most":[80],"effective":[81],"design":[82],"stack":[85],"small":[87],"using":[89],"real-valued":[90],"recurrent":[91],"weights":[92],"local":[95],"convolution,":[96],"allowing":[97],"work":[100],"complementarily.":[101],"Our":[102],"best":[103],"achieves":[105],"WERs":[106],"4.01%/8.53%":[108],"on":[109],"test":[110],"sets":[111],"from":[112],"Librispeech,":[113],"outperforming":[114],"Conformers":[115],"extensively":[117],"tuned":[118],"convolution.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}