{"id":"https://openalex.org/W3135697241","doi":"https://doi.org/10.1109/isscc42613.2021.9366062","title":"9.8 A 25mm<sup>2</sup> SoC for IoT Devices with 18ms Noise-Robust Speech-to-Text Latency via Bayesian Speech Denoising and Attention-Based Sequence-to-Sequence DNN Speech Recognition in 16nm FinFET","display_name":"9.8 A 25mm<sup>2</sup> SoC for IoT Devices with 18ms Noise-Robust Speech-to-Text Latency via Bayesian Speech Denoising and Attention-Based Sequence-to-Sequence DNN Speech Recognition in 16nm FinFET","publication_year":2021,"publication_date":"2021-02-13","ids":{"openalex":"https://openalex.org/W3135697241","doi":"https://doi.org/10.1109/isscc42613.2021.9366062","mag":"3135697241"},"language":"en","primary_location":{"id":"doi:10.1109/isscc42613.2021.9366062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isscc42613.2021.9366062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Solid- State Circuits Conference (ISSCC)","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/A5005762501","display_name":"Thierry Tambe","orcid":"https://orcid.org/0000-0002-6411-9620"},"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":"Thierry Tambe","raw_affiliation_strings":["Harvard University, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088786790","display_name":"En-Yu Yang","orcid":"https://orcid.org/0000-0003-0281-4086"},"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":false,"raw_author_name":"En-Yu Yang","raw_affiliation_strings":["Harvard University, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074229216","display_name":"Glenn G. Ko","orcid":null},"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":false,"raw_author_name":"Glenn G. Ko","raw_affiliation_strings":["Harvard University, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030969018","display_name":"Yuji Chai","orcid":null},"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":false,"raw_author_name":"Yuji Chai","raw_affiliation_strings":["Harvard University, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007438902","display_name":"Coleman Hooper","orcid":"https://orcid.org/0000-0002-5890-610X"},"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":false,"raw_author_name":"Coleman Hooper","raw_affiliation_strings":["Harvard University, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102005543","display_name":"Marco Donato","orcid":"https://orcid.org/0000-0002-9354-3447"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marco Donato","raw_affiliation_strings":["Tufts University, Medford, MA"],"affiliations":[{"raw_affiliation_string":"Tufts University, Medford, MA","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088853105","display_name":"Paul N. Whatmough","orcid":"https://orcid.org/0000-0002-1865-6492"},"institutions":[{"id":"https://openalex.org/I4210156213","display_name":"American Rock Mechanics Association","ror":"https://ror.org/05vfrxy92","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156213"]},{"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":false,"raw_author_name":"Paul N. Whatmough","raw_affiliation_strings":["ARM, Boston, MA","Harvard University, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"ARM, Boston, MA","institution_ids":["https://openalex.org/I4210156213"]},{"raw_affiliation_string":"Harvard University, Cambridge, MA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062546146","display_name":"Alexander M. Rush","orcid":"https://orcid.org/0000-0002-9900-1606"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander M. Rush","raw_affiliation_strings":["Cornell University, New York, NY"],"affiliations":[{"raw_affiliation_string":"Cornell University, New York, NY","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026496503","display_name":"David Brooks","orcid":"https://orcid.org/0000-0002-0662-7889"},"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":false,"raw_author_name":"David Brooks","raw_affiliation_strings":["Harvard University, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043327132","display_name":"Gu-Yeon Wei","orcid":"https://orcid.org/0000-0001-5730-9904"},"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":false,"raw_author_name":"Gu-Yeon Wei","raw_affiliation_strings":["Harvard University, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA","institution_ids":["https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5005762501"],"corresponding_institution_ids":["https://openalex.org/I2801851002"],"apc_list":null,"apc_paid":null,"fwci":3.9143,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.94455211,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"158","last_page":"160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9993000030517578,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.7880827188491821},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7443299293518066},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7080631852149963},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.6433737277984619},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6172900795936584},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5712822675704956},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5550539493560791},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5398641228675842},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5002236366271973},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.46872150897979736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45532914996147156},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.44633516669273376},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4344020187854767},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36569780111312866},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17777058482170105}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7880827188491821},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7443299293518066},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7080631852149963},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.6433737277984619},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6172900795936584},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5712822675704956},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5550539493560791},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5398641228675842},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5002236366271973},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.46872150897979736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45532914996147156},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.44633516669273376},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4344020187854767},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36569780111312866},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17777058482170105},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isscc42613.2021.9366062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isscc42613.2021.9366062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Solid- State Circuits Conference (ISSCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2119944412","https://openalex.org/W2133564696","https://openalex.org/W2766195687","https://openalex.org/W2899441512","https://openalex.org/W2964308564","https://openalex.org/W2965129158","https://openalex.org/W2966841637","https://openalex.org/W3048404194","https://openalex.org/W6766901474"],"related_works":["https://openalex.org/W3161425572","https://openalex.org/W2898867055","https://openalex.org/W3138218066","https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4376480820","https://openalex.org/W3155891479","https://openalex.org/W3029351463"],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"recognition":[2],"(ASR)":[3],"using":[4],"deep":[5,54],"learning":[6,80],"is":[7,127],"essential":[8],"for":[9,62],"user":[10],"interfaces":[11],"on":[12,92,138],"IoT":[13],"devices.":[14],"However,":[15,61],"previously":[16],"published":[17],"ASR":[18,86],"chips":[19],"[4-7]":[20],"do":[21],"not":[22],"consider":[23],"realistic":[24],"operating":[25],"conditions,":[26],"which":[27,84],"are":[28,59,135],"typically":[29],"noisy":[30],"and":[31,149,156],"may":[32],"include":[33],"more":[34,69],"than":[35],"one":[36],"speaker.":[37],"Furthermore,":[38],"several":[39],"of":[40,112,141],"these":[41],"works":[42],"have":[43],"implemented":[44],"only":[45],"small-vocabulary":[46],"tasks,":[47],"such":[48],"as":[49,129],"keyword-spotting":[50],"(KWS),":[51],"where":[52],"context-blind":[53],"neural":[55],"network":[56],"(DNN)":[57],"algorithms":[58],"adequate.":[60],"large-vocabulary":[63],"tasks":[64],"(e.g.,":[65],">100k":[66],"words),":[67],"the":[68,93,108,113,124,139,142],"complex":[70],"bidirectional":[71],"RNNs":[72,146],"with":[73],"an":[74],"attention":[75],"mechanism":[76],"[1]":[77],"provide":[78],"context":[79],"in":[81],"long":[82],"sequences,":[83],"improve":[85],"accuracy":[87],"by":[88,153],"up":[89],"to":[90,98],"62%":[91],"200kwords":[94],"LibriSpeech":[95],"dataset,":[96],"compared":[97],"a":[99,130],"simpler":[100],"unidirectional":[101],"RNN":[102],"(Fig.":[103],"9.8.1).":[104],"Attention-based":[105],"networks":[106],"emphasize":[107],"most":[109],"relevant":[110],"parts":[111],"source":[114],"sequence":[115,126],"during":[116],"each":[117],"decoding":[118],"time":[119,158],"step.":[120],"In":[121],"doing":[122],"so,":[123],"encoder":[125],"treated":[128],"soft-addressable":[131],"memory":[132],"whose":[133],"positions":[134],"weighted":[136],"based":[137],"state":[140],"decoder":[143],"RNN.":[144],"Bidirectional":[145],"learn":[147],"past":[148],"future":[150],"temporal":[151],"information":[152],"concatenating":[154],"forward":[155],"backward":[157],"steps.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}