{"id":"https://openalex.org/W4224917166","doi":"https://doi.org/10.1109/icassp43922.2022.9747800","title":"Run-and-Back Stitch Search: Novel Block Synchronous Decoding For Streaming Encoder-Decoder ASR","display_name":"Run-and-Back Stitch Search: Novel Block Synchronous Decoding For Streaming Encoder-Decoder ASR","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224917166","doi":"https://doi.org/10.1109/icassp43922.2022.9747800"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747800","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5011937407","display_name":"Emiru Tsunoo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emiru Tsunoo","raw_affiliation_strings":["Sony Group Corporation,Japan","Sony Group Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015372147","display_name":"Chaitanya Narisetty","orcid":"https://orcid.org/0000-0002-9239-5534"},"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":"Chaitanya Narisetty","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010628266","display_name":"Michael Hentschel","orcid":"https://orcid.org/0000-0003-3986-5725"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Hentschel","raw_affiliation_strings":["Sony Group Corporation,Japan","Sony Group Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109644502","display_name":"Yosuke Kashiwagi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yosuke Kashiwagi","raw_affiliation_strings":["Sony Group Corporation,Japan","Sony Group Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"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":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3374,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.51368063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"8287","last_page":"8291"},"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/decoding-methods","display_name":"Decoding methods","score":0.8065050840377808},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8038685321807861},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7001115083694458},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6157313585281372},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.48309922218322754},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4177300035953522},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.406474232673645},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3707149624824524},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10517802834510803},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.10160273313522339},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07344937324523926}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.8065050840377808},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8038685321807861},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7001115083694458},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6157313585281372},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48309922218322754},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4177300035953522},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.406474232673645},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3707149624824524},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10517802834510803},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.10160273313522339},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07344937324523926},{"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/icassp43922.2022.9747800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747800","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":32,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W2143612262","https://openalex.org/W2327501763","https://openalex.org/W2766219058","https://openalex.org/W2802023636","https://openalex.org/W2936774411","https://openalex.org/W2962784628","https://openalex.org/W2963242190","https://openalex.org/W2963414781","https://openalex.org/W2973122799","https://openalex.org/W2976556660","https://openalex.org/W2995181338","https://openalex.org/W3007433671","https://openalex.org/W3007528493","https://openalex.org/W3015457435","https://openalex.org/W3015654466","https://openalex.org/W3015671919","https://openalex.org/W3015974384","https://openalex.org/W3095311338","https://openalex.org/W3096702180","https://openalex.org/W3148654612","https://openalex.org/W3162016613","https://openalex.org/W3162665866","https://openalex.org/W3163907627","https://openalex.org/W3209059054","https://openalex.org/W4294619417","https://openalex.org/W6601563604","https://openalex.org/W6623517193","https://openalex.org/W6747158283","https://openalex.org/W6747398299"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2161474341","https://openalex.org/W4302615923","https://openalex.org/W2181948922","https://openalex.org/W1974101135","https://openalex.org/W3203142394","https://openalex.org/W2351061015","https://openalex.org/W2384362569","https://openalex.org/W2017509870","https://openalex.org/W4220731478"],"abstract_inverted_index":{"A":[0],"streaming":[1],"style":[2],"inference":[3],"of":[4,53,56,68,102,112,145,152],"encoder\u2013decoder":[5],"automatic":[6],"speech":[7],"recognition":[8,183],"(ASR)":[9],"systems":[10],"is":[11,17,107],"important":[12],"for":[13,19,162],"reducing":[14],"latency,":[15],"which":[16,106,137,157],"essential":[18],"interactive":[20],"use":[21],"cases.":[22],"To":[23],"this":[24],"end,":[25],"we":[26,49],"propose":[27],"a":[28,35,92,130,159,181],"novel":[29],"blockwise":[30],"synchronous":[31],"decoding":[32,117,155],"algorithm":[33],"with":[34],"hybrid":[36,131],"approach":[37],"that":[38,58],"combines":[39],"endpoint":[40,43,47,85],"prediction":[41],"and":[42,142],"post-determination.":[44],"In":[45],"the":[46,51,54,65,69,73,78,81,84,103,110,139,150,165,176],"prediction,":[48],"compute":[50],"expectation":[52,79],"number":[55],"tokens":[57],"are":[59],"yet":[60],"to":[61,86,172],"be":[62],"emitted":[63],"in":[64,164],"encoder":[66],"features":[67],"current":[70],"blocks":[71],"using":[72],"CTC":[74],"posterior.":[75],"Based":[76],"on":[77],"value,":[80],"decoder":[82],"predicts":[83],"realize":[87],"continuous":[88],"block":[89],"synchronization,":[90],"as":[91,122],"running":[93],"stitch.":[94,124],"Meanwhile,":[95],"end-point":[96],"post-determination":[97],"probabilistically":[98],"detects":[99],"backward":[100],"jump":[101],"source\u2013target":[104],"attention,":[105],"caused":[108],"by":[109,118],"misprediction":[111],"endpoints.":[113],"Then":[114],"it":[115],"resumes":[116],"discarding":[119],"those":[120],"hypotheses,":[121],"back":[123],"We":[125],"combine":[126],"these":[127],"methods":[128],"into":[129],"approach,":[132],"namely":[133],"run-and-back":[134],"stitch":[135],"search,":[136],"reduces":[138],"computational":[140],"cost":[141],"latency.":[143],"Evaluations":[144],"various":[146],"ASR":[147],"tasks":[148],"show":[149],"efficiency":[151],"our":[153],"proposed":[154],"algorithm,":[156],"achieves":[158],"latency":[160],"reduction,":[161],"instance":[163],"Librispeech":[166],"test":[167],"set":[168],"from":[169],"1487":[170],"ms":[171,174],"821":[173],"at":[175],"90th":[177],"percentile,":[178],"while":[179],"maintaining":[180],"high":[182],"accuracy.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}