{"id":"https://openalex.org/W4408352636","doi":"https://doi.org/10.1109/icassp49660.2025.10887599","title":"Mamba for Streaming ASR Combined with Unimodal Aggregation","display_name":"Mamba for Streaming ASR Combined with Unimodal Aggregation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352636","doi":"https://doi.org/10.1109/icassp49660.2025.10887599"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5119309726","display_name":"Ying Fang","orcid":"https://orcid.org/0009-0003-8767-1172"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Fang","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100358300","display_name":"Xiaofei Li","orcid":"https://orcid.org/0000-0002-5443-3042"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei Li","raw_affiliation_strings":["Westlake University,School of Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westlake University,School of Engineering,China","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T12222","display_name":"IoT-based Smart Home Systems","score":0.9189000129699707,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12222","display_name":"IoT-based Smart Home Systems","score":0.9189000129699707,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6124004125595093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6124004125595093}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":25,"referenced_works":["https://openalex.org/W2039847325","https://openalex.org/W2127141656","https://openalex.org/W2747874407","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W3007433671","https://openalex.org/W3015974384","https://openalex.org/W3016010032","https://openalex.org/W3016167541","https://openalex.org/W3097777922","https://openalex.org/W3163907627","https://openalex.org/W4225277656","https://openalex.org/W4372259877","https://openalex.org/W4372346832","https://openalex.org/W4372349820","https://openalex.org/W4375869369","https://openalex.org/W4392910797","https://openalex.org/W4402112292","https://openalex.org/W4408352482","https://openalex.org/W4410087476","https://openalex.org/W6754473786","https://openalex.org/W6787040858","https://openalex.org/W6852638770","https://openalex.org/W6859298233","https://openalex.org/W6868789466"],"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":{"This":[0],"paper":[1],"works":[2],"on":[3,86,102],"streaming":[4,43],"automatic":[5],"speech":[6],"recognition":[7,98,120],"(ASR).":[8],"Mamba,":[9],"a":[10,31,57],"recently":[11],"proposed":[12,94,110],"state":[13],"space":[14],"model,":[15],"has":[16],"demonstrated":[17],"the":[18,37,109],"ability":[19],"to":[20,95],"match":[21],"or":[22],"surpass":[23],"Transformers":[24],"in":[25,116],"various":[26],"tasks":[27],"while":[28],"benefiting":[29],"from":[30],"linear":[32],"complexity":[33],"advantage.":[34],"We":[35],"explore":[36],"efficiency":[38],"of":[39,118],"Mamba":[40],"encoder":[41],"for":[42,51,80],"ASR":[44,114],"and":[45,70,75,122],"propose":[46],"an":[47,88],"associated":[48],"lookahead":[49],"mechanism":[50],"leveraging":[52],"controllable":[53],"future":[54],"information.":[55],"Additionally,":[56],"streaming-style":[58],"unimodal":[59],"aggregation":[60],"(UMA)":[61],"method":[62,92],"is":[63,93],"implemented,":[64],"which":[65],"automatically":[66],"detects":[67],"token":[68,73,83],"activity":[69],"streamingly":[71],"triggers":[72],"output,":[74],"meanwhile":[76],"aggregates":[77],"feature":[78],"frames":[79],"better":[81],"learning":[82],"representation.":[84],"Based":[85],"UMA,":[87],"early":[89],"termination":[90],"(ET)":[91],"further":[96],"reduce":[97],"latency.":[99,123],"Experiments":[100],"conducted":[101],"two":[103],"Mandarin":[104],"Chinese":[105],"datasets":[106],"demonstrate":[107],"that":[108],"model":[111],"achieves":[112],"competitive":[113],"performance":[115],"terms":[117],"both":[119],"accuracy":[121],"Code":[124],"will":[125],"be":[126],"open-sourced":[127],"<sup":[128],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[129],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}