{"id":"https://openalex.org/W2046317185","doi":"https://doi.org/10.1109/icassp.2014.6854639","title":"Deep learning of split temporal context for automatic speech recognition","display_name":"Deep learning of split temporal context for automatic speech recognition","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2046317185","doi":"https://doi.org/10.1109/icassp.2014.6854639","mag":"2046317185"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/A5054284441","display_name":"Moez Baccouche","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Moez Baccouche","raw_affiliation_strings":["Orange Labs - France T\u00e9l\u00e9com, Cesson-S\u00e9vign\u00e9, France","Orange Labs., France Telecom, Cesson-Se\u0301vigne\u0301, France"],"affiliations":[{"raw_affiliation_string":"Orange Labs - France T\u00e9l\u00e9com, Cesson-S\u00e9vign\u00e9, France","institution_ids":["https://openalex.org/I19370010"]},{"raw_affiliation_string":"Orange Labs., France Telecom, Cesson-Se\u0301vigne\u0301, France","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067827147","display_name":"Benoit Besset","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Benoit Besset","raw_affiliation_strings":["Orange Labs - France T\u00e9l\u00e9com, Cesson-S\u00e9vign\u00e9, France","Orange Labs., France Telecom, Cesson-Se\u0301vigne\u0301, France"],"affiliations":[{"raw_affiliation_string":"Orange Labs - France T\u00e9l\u00e9com, Cesson-S\u00e9vign\u00e9, France","institution_ids":["https://openalex.org/I19370010"]},{"raw_affiliation_string":"Orange Labs., France Telecom, Cesson-Se\u0301vigne\u0301, France","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064490203","display_name":"Patrice Collen","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Patrice Collen","raw_affiliation_strings":["Orange Labs - France T\u00e9l\u00e9com, Cesson-S\u00e9vign\u00e9, France","Orange Labs., France Telecom, Cesson-Se\u0301vigne\u0301, France"],"affiliations":[{"raw_affiliation_string":"Orange Labs - France T\u00e9l\u00e9com, Cesson-S\u00e9vign\u00e9, France","institution_ids":["https://openalex.org/I19370010"]},{"raw_affiliation_string":"Orange Labs., France Telecom, Cesson-Se\u0301vigne\u0301, France","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010074905","display_name":"Olivier Le Blouch","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Le Blouch","raw_affiliation_strings":["Orange Labs - France T\u00e9l\u00e9com, Cesson-S\u00e9vign\u00e9, France","Orange Labs., France Telecom, Cesson-Se\u0301vigne\u0301, France"],"affiliations":[{"raw_affiliation_string":"Orange Labs - France T\u00e9l\u00e9com, Cesson-S\u00e9vign\u00e9, France","institution_ids":["https://openalex.org/I19370010"]},{"raw_affiliation_string":"Orange Labs., France Telecom, Cesson-Se\u0301vigne\u0301, France","institution_ids":["https://openalex.org/I19370010"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054284441"],"corresponding_institution_ids":["https://openalex.org/I19370010"],"apc_list":null,"apc_paid":null,"fwci":1.636,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87220954,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998000264167786,"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":0.9995999932289124,"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/computer-science","display_name":"Computer science","score":0.8226029872894287},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.650819718837738},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5624862909317017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5136319994926453},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4980275630950928}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8226029872894287},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.650819718837738},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5624862909317017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5136319994926453},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4980275630950928},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W155708904","https://openalex.org/W169882265","https://openalex.org/W186915233","https://openalex.org/W192024671","https://openalex.org/W217970951","https://openalex.org/W1517386993","https://openalex.org/W1984541135","https://openalex.org/W1993882792","https://openalex.org/W1994197834","https://openalex.org/W2013598660","https://openalex.org/W2014641584","https://openalex.org/W2036242736","https://openalex.org/W2077804127","https://openalex.org/W2100495367","https://openalex.org/W2103359087","https://openalex.org/W2110798204","https://openalex.org/W2114992418","https://openalex.org/W2116064496","https://openalex.org/W2125534887","https://openalex.org/W2131700150","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2155273149","https://openalex.org/W2156373089","https://openalex.org/W2167763959","https://openalex.org/W2168171912","https://openalex.org/W6606278960","https://openalex.org/W6606983177","https://openalex.org/W6607530402","https://openalex.org/W6607789788","https://openalex.org/W6608710415","https://openalex.org/W6653960356","https://openalex.org/W6675321185","https://openalex.org/W6676481782"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W2939353110","https://openalex.org/W4321369474","https://openalex.org/W4360585206","https://openalex.org/W4285208911","https://openalex.org/W4213079790","https://openalex.org/W2248239756","https://openalex.org/W2773120646"],"abstract_inverted_index":{"This":[0,72],"paper":[1],"follows":[2],"the":[3,12,36,47,80,99,105,115,119],"recent":[4],"advances":[5],"in":[6],"speech":[7],"recognition":[8,28],"which":[9,61],"recommend":[10],"replacing":[11],"standard":[13],"hybrid":[14],"GMM/HMM":[15],"approach":[16,96,132],"by":[17],"deep":[18,90,107],"neural":[19],"architectures.":[20],"These":[21],"models":[22],"were":[23],"shown":[24],"to":[25,31,34,104,135,144],"drastically":[26],"improve":[27],"performances,":[29],"due":[30],"their":[32],"ability":[33],"capture":[35],"underlying":[37],"structure":[38],"of":[39,51,69,101,121,138],"data.":[40],"However,":[41],"they":[42],"remain":[43],"particularly":[44],"complex":[45],"since":[46],"entire":[48],"temporal":[49,81],"context":[50,82],"a":[52,58,65,88,124],"given":[53],"phoneme":[54],"is":[55,133],"learned":[56,86],"with":[57,87],"single":[59],"model,":[60],"must":[62],"therefore":[63],"have":[64],"very":[66],"large":[67],"number":[68,100],"trainable":[70],"weights.":[71],"work":[73],"proposes":[74],"an":[75],"alternative":[76],"solution":[77],"that":[78,94,130],"splits":[79],"into":[83],"blocks,":[84],"each":[85],"separate":[89],"model.":[91],"We":[92,127],"demonstrate":[93],"this":[95],"significantly":[97],"reduces":[98],"parameters":[102],"compared":[103],"classical":[106],"learning":[108],"procedure,":[109],"and":[110],"obtains":[111],"better":[112],"results":[113],"on":[114],"TIMIT":[116],"dataset,":[117],"among":[118],"best":[120],"state-of-the-art":[122],"(with":[123],"20.20%":[125],"PER).":[126],"also":[128],"show":[129],"our":[131],"able":[134],"assimilate":[136],"data":[137],"different":[139],"nature,":[140],"ranging":[141],"from":[142],"wide":[143],"narrow":[145],"bandwidth":[146],"signals.":[147]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}