{"id":"https://openalex.org/W2890297197","doi":"https://doi.org/10.1109/icassp.2018.8462615","title":"Dynamic Frame Skipping for Fast Speech Recognition in Recurrent Neural Network Based Acoustic Models","display_name":"Dynamic Frame Skipping for Fast Speech Recognition in Recurrent Neural Network Based Acoustic Models","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2890297197","doi":"https://doi.org/10.1109/icassp.2018.8462615","mag":"2890297197"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5109866178","display_name":"Inchul Song","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Inchul Song","raw_affiliation_strings":["Republic of Korea, Samsung Advanced Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Republic of Korea, Samsung Advanced Institute of Technology","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044550553","display_name":"Jun\u2010Young Chung","orcid":"https://orcid.org/0000-0002-7408-8215"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Junyoung Chung","raw_affiliation_strings":["MILA, Universit\u00e9 de Montr\u00e9al, Canada"],"affiliations":[{"raw_affiliation_string":"MILA, Universit\u00e9 de Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065728469","display_name":"Taesup Kim","orcid":"https://orcid.org/0000-0002-8357-1700"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Taesup Kim","raw_affiliation_strings":["MILA, Universit\u00e9 de Montr\u00e9al, Canada"],"affiliations":[{"raw_affiliation_string":"MILA, Universit\u00e9 de Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086198262","display_name":"Yoshua Bengio","orcid":"https://orcid.org/0000-0002-9322-3515"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoshua Bengio","raw_affiliation_strings":["Republic of Korea, Samsung Advanced Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Republic of Korea, Samsung Advanced Institute of Technology","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109866178"],"corresponding_institution_ids":["https://openalex.org/I2250650973"],"apc_list":null,"apc_paid":null,"fwci":1.1402,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.83843122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"3","issue":null,"first_page":"4984","last_page":"4988"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9969000220298767,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965000152587891,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.9026513695716858},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8491175174713135},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.7378969788551331},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6834415793418884},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.6820881366729736},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.681790292263031},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.48655858635902405},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4692677855491638},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45428466796875},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44898584485054016},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42850661277770996},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08763381838798523}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.9026513695716858},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8491175174713135},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.7378969788551331},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6834415793418884},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.6820881366729736},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.681790292263031},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.48655858635902405},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4692677855491638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45428466796875},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44898584485054016},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42850661277770996},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08763381838798523},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"},{"id":"https://openalex.org/F4320320994","display_name":"Canada Research Chairs","ror":"https://ror.org/0517h6h17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1489125746","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1984446451","https://openalex.org/W2005708641","https://openalex.org/W2010291496","https://openalex.org/W2024490156","https://openalex.org/W2064675550","https://openalex.org/W2110707300","https://openalex.org/W2119717200","https://openalex.org/W2160815625","https://openalex.org/W2293634267","https://openalex.org/W2396384435","https://openalex.org/W2515439472","https://openalex.org/W2951527505","https://openalex.org/W2953384591","https://openalex.org/W2964043796","https://openalex.org/W4214717370","https://openalex.org/W6631362777","https://openalex.org/W6676284021","https://openalex.org/W6677916085","https://openalex.org/W6682137061","https://openalex.org/W6692846177","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W2160451571","https://openalex.org/W2109916967","https://openalex.org/W2495256954","https://openalex.org/W2259317772","https://openalex.org/W2101697354","https://openalex.org/W1538193578","https://openalex.org/W3206636855","https://openalex.org/W1538606284","https://openalex.org/W2890297197","https://openalex.org/W2888189389"],"abstract_inverted_index":{"A":[0],"recurrent":[1,18,44,77],"neural":[2,19,45,78],"network":[3,79,99,102],"is":[4,31,62],"a":[5,75],"powerful":[6],"tool":[7],"for":[8],"modeling":[9],"sequential":[10],"data":[11],"such":[12],"as":[13],"text":[14],"and":[15,100,111,129],"speech.":[16],"While":[17],"networks":[20,46],"have":[21],"achieved":[22],"record-breaking":[23],"results":[24],"in":[25,147],"speech":[26,86,109],"recognition,":[27],"one":[28,50],"remaining":[29],"challenge":[30],"their":[32],"slow":[33],"processing":[34,68],"speed.":[35],"The":[36,92],"main":[37],"cause":[38],"comes":[39],"from":[40],"the":[41,58,124],"nature":[42],"of":[43,60,95],"that":[47,88,103,131],"read":[48],"only":[49],"frame":[51],"at":[52],"each":[53],"time":[54],"step.":[55],"Therefore,":[56],"reducing":[57,67],"number":[59],"reads":[61],"an":[63,96],"effective":[64],"approach":[65,122],"to":[66,107,116,140],"time.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"propose":[74],"novel":[76],"architecture":[80],"called":[81],"Skip-RNN,":[82],"which":[83],"dynamically":[84],"skips":[85],"frames":[87,110,115],"are":[89,104],"less":[90],"important.":[91],"Skip-RNN":[93],"consists":[94],"acoustic":[97,135],"model":[98,136],"skip-policy":[101],"jointly":[105],"trained":[106],"classify":[108],"determine":[112],"how":[113],"many":[114],"skip.":[117],"We":[118],"evaluate":[119],"our":[120],"proposed":[121],"on":[123],"Wall":[125],"Street":[126],"Journal":[127],"corpus":[128],"show":[130],"it":[132],"can":[133],"accelerate":[134],"computation":[137],"by":[138],"up":[139],"2.4":[141],"times":[142],"without":[143],"any":[144],"noticeable":[145],"degradation":[146],"transcription":[148],"accuracy.":[149]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}