{"id":"https://openalex.org/W2010291496","doi":"https://doi.org/10.1109/icassp.2013.6639137","title":"Multiframe deep neural networks for acoustic modeling","display_name":"Multiframe deep neural networks for acoustic modeling","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2010291496","doi":"https://doi.org/10.1109/icassp.2013.6639137","mag":"2010291496"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5013813527","display_name":"Vincent Vanhoucke","orcid":"https://orcid.org/0000-0003-0544-2791"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vincent Vanhoucke","raw_affiliation_strings":["Google, Inc., USA","Google Inc., Mountain View, CA USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004386681","display_name":"Matthieu Devin","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthieu Devin","raw_affiliation_strings":["Google, Inc., USA","Google Inc., Mountain View, CA USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071956319","display_name":"Georg Heigold","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Georg Heigold","raw_affiliation_strings":["Google, Inc., USA","Google Inc., Mountain View, CA USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013813527"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":11.8616,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.98366072,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7582","last_page":"7585"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.7909460067749023},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7663074731826782},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6074061989784241},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5846862196922302},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5565379858016968},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4838665723800659},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4756757318973541},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4646930396556854},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45848438143730164},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.4286792278289795},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.42331135272979736},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42185696959495544},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10241761803627014}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7909460067749023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7663074731826782},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6074061989784241},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5846862196922302},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5565379858016968},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4838665723800659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4756757318973541},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4646930396556854},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45848438143730164},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.4286792278289795},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.42331135272979736},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42185696959495544},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10241761803627014},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.2471","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.2471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/pubs/archive/40810.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W587794757","https://openalex.org/W1984446451","https://openalex.org/W2110707300","https://openalex.org/W2144792281","https://openalex.org/W2146502635","https://openalex.org/W2160815625","https://openalex.org/W2168231600","https://openalex.org/W2184045248","https://openalex.org/W2394932179","https://openalex.org/W2899506040","https://openalex.org/W6617368339","https://openalex.org/W6676284021","https://openalex.org/W6681435938","https://openalex.org/W6684859321","https://openalex.org/W6756028334"],"related_works":["https://openalex.org/W2977517636","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W3000197790","https://openalex.org/W1969179582","https://openalex.org/W4315865067","https://openalex.org/W2979433843","https://openalex.org/W3208304128","https://openalex.org/W2810129309"],"abstract_inverted_index":{"Deep":[0],"neural":[1,42,74,104,131],"networks":[2,43,75],"have":[3],"been":[4],"shown":[5],"to":[6,18,24,32,47,56,68,93,113,121],"perform":[7],"very":[8,26,50,61],"well":[9],"as":[10],"acoustic":[11],"models":[12],"for":[13],"automatic":[14],"speech":[15],"recognition.":[16],"Compared":[17],"Gaussian":[19],"mixtures":[20],"however,":[21],"they":[22],"tend":[23],"be":[25,90],"expensive":[27],"computationally,":[28],"making":[29],"them":[30],"challenging":[31],"use":[33],"in":[34,125],"real-time":[35],"applications.":[36],"One":[37],"key":[38],"advantage":[39],"of":[40,101,129],"such":[41],"is":[44,66],"their":[45],"ability":[46],"learn":[48],"from":[49],"long":[51,62],"observation":[52],"windows":[53],"going":[54],"up":[55,120],"400":[57],"ms.":[58],"Given":[59],"this":[60],"temporal":[63],"context,":[64],"it":[65],"tempting":[67],"wonder":[69],"whether":[70,87],"one":[71],"can":[72],"run":[73],"at":[76],"a":[77,99,122],"lower":[78],"frame":[79],"rate":[80],"than":[81],"the":[82,103,114,126,130],"typical":[83,115],"10":[84],"ms,":[85],"and":[86],"there":[88],"might":[89],"computational":[91,127],"benefits":[92],"doing":[94],"so.":[95],"This":[96],"paper":[97],"describes":[98],"method":[100],"tying":[102],"network":[105,132],"parameters":[106],"over":[107],"time":[108],"which":[109],"achieves":[110],"comparable":[111],"performance":[112],"frame-synchronous":[116],"model,":[117],"while":[118],"achieving":[119],"4X":[123],"reduction":[124],"cost":[128],"activations.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}