{"id":"https://openalex.org/W4408355618","doi":"https://doi.org/10.1109/icassp49660.2025.10889802","title":"Advancing Streaming ASR with Chunk-wise Attention and Trans-chunk Selective State Spaces","display_name":"Advancing Streaming ASR with Chunk-wise Attention and Trans-chunk Selective State Spaces","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355618","doi":"https://doi.org/10.1109/icassp49660.2025.10889802"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889802","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/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000803465","display_name":"Kohei Matsuura","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kohei Matsuura","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10876","display_name":"Fault Detection and Control Systems","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9678000211715698,"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/T12676","display_name":"Machine Learning and ELM","score":0.9435999989509583,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7679125666618347},{"id":"https://openalex.org/keywords/selective-attention","display_name":"Selective attention","score":0.5347669720649719},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43236973881721497},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37597984075546265},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3206413686275482},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11433449387550354},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09428480267524719},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.08755049109458923},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.05593353509902954}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7679125666618347},{"id":"https://openalex.org/C2989146674","wikidata":"https://www.wikidata.org/wiki/Q4818236","display_name":"Selective attention","level":3,"score":0.5347669720649719},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43236973881721497},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37597984075546265},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3206413686275482},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11433449387550354},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09428480267524719},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.08755049109458923},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.05593353509902954}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889802","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2962784628","https://openalex.org/W2962826786","https://openalex.org/W2963925437","https://openalex.org/W2964084166","https://openalex.org/W2972389417","https://openalex.org/W3008181812","https://openalex.org/W3016010032","https://openalex.org/W3094543484","https://openalex.org/W3097777922","https://openalex.org/W3160766462","https://openalex.org/W3161873870","https://openalex.org/W3163842642","https://openalex.org/W3163907627","https://openalex.org/W3209059054","https://openalex.org/W4210327373","https://openalex.org/W4226120743","https://openalex.org/W4283700324","https://openalex.org/W4297727296","https://openalex.org/W4313442864","https://openalex.org/W4372349820","https://openalex.org/W4375869285","https://openalex.org/W4385822815","https://openalex.org/W4392910298","https://openalex.org/W4402111418","https://openalex.org/W4402112450","https://openalex.org/W4402112499","https://openalex.org/W4406461620","https://openalex.org/W4408353174","https://openalex.org/W6631190155","https://openalex.org/W6691770337","https://openalex.org/W6739901393","https://openalex.org/W6744720862","https://openalex.org/W6780218876","https://openalex.org/W6782420349","https://openalex.org/W6790121257","https://openalex.org/W6803444062","https://openalex.org/W6809915218","https://openalex.org/W6810673746","https://openalex.org/W6839026989","https://openalex.org/W6839235732","https://openalex.org/W6847568899","https://openalex.org/W6849840618","https://openalex.org/W6850033884","https://openalex.org/W6852638770","https://openalex.org/W6859298233","https://openalex.org/W6862598229","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],"explores":[2],"enhancing":[3],"streaming":[4,105],"speech":[5,90,106],"recognition":[6,107],"through":[7],"the":[8,23,54,94,98,110],"integration":[9],"of":[10,26,53,97],"chunk-wise":[11,61],"attention":[12,78,113],"and":[13,43,112,121],"selective":[14,37,44],"state":[15],"space":[16],"models":[17],"(SSMs).":[18],"The":[19],"proposed":[20],"framework":[21],"replaces":[22],"quadratic":[24],"complexity":[25],"attention-based":[27],"context":[28,70],"incorporation":[29],"with":[30],"a":[31,67],"fully":[32],"recurrent":[33,48,111],"module":[34,49,79],"based":[35],"on":[36,85],"SSMs.":[38],"Leveraging":[39],"its":[40],"constant-time":[41],"inference":[42],"reasoning":[45],"capability,":[46],"our":[47,76],"efficiently":[50],"takes":[51],"advantage":[52],"entire":[55],"history":[56],"across":[57],"chunks,":[58],"while":[59],"conventional":[60],"encoders":[62],"are":[63],"typically":[64],"constrained":[65],"to":[66,71,82,126],"fixed-length":[68],"left":[69],"ensure":[72],"real-time":[73],"performance.":[74],"Meanwhile,":[75],"within-chunk":[77],"is":[80],"designed":[81],"focus":[83],"exclusively":[84],"local":[86],"features":[87],"within":[88],"short":[89],"segments,":[91],"thereby":[92],"complementing":[93],"autoregressive":[95],"behavior":[96],"SSM.":[99],"Experimental":[100],"results":[101],"from":[102],"RNN":[103],"Transducer-based":[104],"indicate":[108],"that":[109],"modules":[114],"work":[115],"synergistically,":[116],"yielding":[117],"lower":[118],"error":[119],"rates":[120],"reduced":[122],"runtime":[123],"costs":[124],"compared":[125],"baseline":[127],"Conformer":[128],"systems.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}