{"id":"https://openalex.org/W2696248230","doi":"https://doi.org/10.1109/icassp.2017.7952665","title":"Reducing total latency in online real-time inference and decoding via combined context window and model smoothing latencies","display_name":"Reducing total latency in online real-time inference and decoding via combined context window and model smoothing latencies","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2696248230","doi":"https://doi.org/10.1109/icassp.2017.7952665","mag":"2696248230"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5058760668","display_name":"Chandrashekhar Lavania","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chandrashekhar Lavania","raw_affiliation_strings":["Department Of Electrical Engineering, University Of Washington, Seattle, USA"],"affiliations":[{"raw_affiliation_string":"Department Of Electrical Engineering, University Of Washington, Seattle, USA","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113478221","display_name":"Jeff Bilmes","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeff Bilmes","raw_affiliation_strings":["Department Of Electrical Engineering, University Of Washington, Seattle, USA"],"affiliations":[{"raw_affiliation_string":"Department Of Electrical Engineering, University Of Washington, Seattle, USA","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5058760668"],"corresponding_institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"],"apc_list":null,"apc_paid":null,"fwci":0.5851,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75065213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2015","issue":null,"first_page":"2791","last_page":"2795"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9970999956130981,"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9970999956130981,"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":0.996399998664856,"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/T10320","display_name":"Neural Networks and Applications","score":0.995199978351593,"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":0.8022884130477905},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.7703094482421875},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7355474233627319},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6909526586532593},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6124561429023743},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5371058583259583},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.470418244600296},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44368234276771545},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.4255332052707672},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40163877606391907},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3313196301460266},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23897919058799744},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.20895028114318848},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10002031922340393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8022884130477905},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.7703094482421875},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7355474233627319},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6909526586532593},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6124561429023743},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5371058583259583},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.470418244600296},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44368234276771545},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.4255332052707672},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40163877606391907},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3313196301460266},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23897919058799744},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.20895028114318848},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10002031922340393},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7952665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/W811578723","https://openalex.org/W1499864241","https://openalex.org/W1581808154","https://openalex.org/W1904365287","https://openalex.org/W1987841215","https://openalex.org/W2033285509","https://openalex.org/W2040118574","https://openalex.org/W2064082346","https://openalex.org/W2077804127","https://openalex.org/W2089177488","https://openalex.org/W2102113734","https://openalex.org/W2112739286","https://openalex.org/W2122678358","https://openalex.org/W2124521682","https://openalex.org/W2125496931","https://openalex.org/W2126514931","https://openalex.org/W2134797427","https://openalex.org/W2139034093","https://openalex.org/W2143612262","https://openalex.org/W2146502635","https://openalex.org/W2155273149","https://openalex.org/W2155893237","https://openalex.org/W2159080219","https://openalex.org/W6675365184","https://openalex.org/W6679128827","https://openalex.org/W6679909955","https://openalex.org/W6681435938"],"related_works":["https://openalex.org/W1978572805","https://openalex.org/W2383807498","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W4238188170","https://openalex.org/W2585772085","https://openalex.org/W3128807919","https://openalex.org/W3176411177","https://openalex.org/W2510935666","https://openalex.org/W3097264971"],"abstract_inverted_index":{"Real-time":[0],"low-latency":[1,120],"online":[2],"inference":[3,27],"and":[4,21,55,111],"decoding":[5],"in":[6,12,30,50,62],"sequential":[7],"probabilistic":[8,65],"models":[9],"are":[10],"important":[11],"many":[13],"interactive":[14],"systems,":[15,32],"including":[16],"automatic":[17],"speech":[18],"recognition":[19],"(ASR)":[20],"streaming":[22],"environments.":[23],"We":[24],"study":[25],"total":[26],"latency":[28,36,57],"(TL)":[29],"such":[31],"the":[33,38,56,78,97,123],"additively":[34],"combined":[35],"of":[37,41,125],"inherent":[39],"look-ahead":[40],"a":[42,51,63,75,84,91,93,126],"deep":[43],"neural":[44],"network's":[45],"(DNN)":[46],"contextual":[47],"window":[48,129],"(CWL)":[49],"DNN-HMM":[52],"hybrid":[53],"system":[54],"incurred":[58],"during":[59],"Kalman-style":[60],"smoothing":[61,133],"dynamic":[64],"model":[66,132],"(MSL)":[67],"(hence,":[68],"TL":[69,110],"=":[70],"CWL":[71],"+":[72],"MSL).":[73],"For":[74],"fixed":[76],"TL,":[77],"best":[79],"accuracy":[80,104],"can":[81],"occur":[82],"with":[83,108,131],"strictly":[85],"positive":[86],"MSL,":[87],"often":[88,106],"by":[89],"quite":[90],"bit,":[92],"surprising":[94],"result":[95],"given":[96],"DNN's":[98],"power.":[99],"Furthermore,":[100],"we":[101],"find":[102],"that":[103,117],"is":[105],"improved":[107],"smaller":[109],"larger":[112],"MSL.":[113],"These":[114],"results":[115],"suggest":[116],"for":[118],"optimal":[119],"real-time":[121],"decoding,":[122],"size":[124],"DNN":[127],"context":[128],"along":[130],"should":[134],"be":[135],"jointly":[136],"considered.":[137]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}