{"id":"https://openalex.org/W2753094133","doi":"https://doi.org/10.1147/jrd.2017.2701178","title":"Recent advances in conversational speech recognition using convolutional and recurrent neural networks","display_name":"Recent advances in conversational speech recognition using convolutional and recurrent neural networks","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2753094133","doi":"https://doi.org/10.1147/jrd.2017.2701178","mag":"2753094133"},"language":"en","primary_location":{"id":"doi:10.1147/jrd.2017.2701178","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2017.2701178","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","raw_type":"journal-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/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"G. Saon","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M. Picheny","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079994647"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9253,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.92979365,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"61","issue":"4/5","first_page":"1:1","last_page":"1:10"},"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":0.9983999729156494,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"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":0.8058151006698608},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7634401321411133},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7548518180847168},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6456079483032227},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6408678889274597},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6165681481361389},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6062442064285278},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5668103694915771},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5641278028488159},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5121526718139648},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.47554728388786316},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.4355723261833191},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.42475682497024536},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4245019257068634},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35925108194351196},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34163913130760193},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33772042393684387},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.13650164008140564},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08506649732589722}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8058151006698608},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7634401321411133},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7548518180847168},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6456079483032227},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6408678889274597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6165681481361389},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6062442064285278},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5668103694915771},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5641278028488159},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5121526718139648},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.47554728388786316},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.4355723261833191},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.42475682497024536},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4245019257068634},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35925108194351196},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34163913130760193},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33772042393684387},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.13650164008140564},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08506649732589722},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1147/jrd.2017.2701178","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2017.2701178","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W11314411","https://openalex.org/W97072897","https://openalex.org/W1533416326","https://openalex.org/W1598897937","https://openalex.org/W1686810756","https://openalex.org/W1797288984","https://openalex.org/W1922655562","https://openalex.org/W1924770834","https://openalex.org/W1998656041","https://openalex.org/W2002342963","https://openalex.org/W2028706510","https://openalex.org/W2050971845","https://openalex.org/W2064675550","https://openalex.org/W2079623482","https://openalex.org/W2097599384","https://openalex.org/W2104448323","https://openalex.org/W2105024701","https://openalex.org/W2114016253","https://openalex.org/W2124537004","https://openalex.org/W2127095586","https://openalex.org/W2131342762","https://openalex.org/W2136848157","https://openalex.org/W2143612262","https://openalex.org/W2144790469","https://openalex.org/W2158195707","https://openalex.org/W2166637769","https://openalex.org/W2168941687","https://openalex.org/W2184045248","https://openalex.org/W2198724430","https://openalex.org/W2288502450","https://openalex.org/W2394932179","https://openalex.org/W2396033037","https://openalex.org/W2400505028","https://openalex.org/W2403195671","https://openalex.org/W2507436421","https://openalex.org/W2514741789","https://openalex.org/W2533523411","https://openalex.org/W2962719052","https://openalex.org/W2962835968","https://openalex.org/W2963211739","https://openalex.org/W2963266252","https://openalex.org/W2963490782","https://openalex.org/W2963795358","https://openalex.org/W4205897042","https://openalex.org/W4249003657","https://openalex.org/W4285719527","https://openalex.org/W6600493724","https://openalex.org/W6603931906","https://openalex.org/W6637373629","https://openalex.org/W6638218882","https://openalex.org/W6639288305","https://openalex.org/W6640090968","https://openalex.org/W6640212811","https://openalex.org/W6679429981","https://openalex.org/W6686210252","https://openalex.org/W6711802761","https://openalex.org/W6711962127","https://openalex.org/W6712772800","https://openalex.org/W6713280142","https://openalex.org/W6728841359"],"related_works":["https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W3034302643","https://openalex.org/W1847088711","https://openalex.org/W4225394202","https://openalex.org/W3036642985","https://openalex.org/W2610189143","https://openalex.org/W1997182898","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Deep":[0],"learning":[1,16,30],"methodologies":[2],"have":[3],"had":[4],"a":[5,11,26,49,108,120,138],"major":[6],"impact":[7],"on":[8,48,144,175],"performance":[9,40,64,168],"across":[10],"wide":[12],"variety":[13],"of":[14,28,100,142,157],"machine":[15],"tasks,":[17],"and":[18,73,88,115,126,160],"speech":[19,54],"recognition":[20,55],"is":[21,65,161,170],"no":[22],"exception.":[23],"We":[24,59,77],"describe":[25],"set":[27],"deep":[29],"techniques":[31],"that":[32,61,118,166],"proved":[33],"to":[34,172],"be":[35,173],"particularly":[36],"successful":[37],"in":[38,42],"achieving":[39],"gains":[41],"<italic":[43],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[44],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">word":[45],"error":[46,140],"rate</i>":[47],"popular":[50],"large":[51],"vocabulary":[52],"conversational":[53],"benchmark":[56],"task":[57],"(\u201cSwitchboard\u201d).":[58],"found":[60],"the":[62,98,150,155],"best":[63,151],"achieved":[66],"by":[67,97],"combining":[68],"features":[69],"from":[70],"both":[71],"recurrent":[72,80],"convolutional":[74,101,109,113],"neural":[75,135],"networks.":[76],"compare":[78],"two":[79],"architectures:":[81],"partially":[82],"unfolded":[83],"nets":[84],"with":[85,111,123],"max-out":[86],"activations":[87],"bidirectional":[89],"long":[90],"short-term":[91],"memory":[92],"nets.":[93],"In":[94],"addition,":[95],"inspired":[96],"success":[99],"networks":[102,136],"for":[103],"image":[104],"classification,":[105],"we":[106],"designed":[107],"net":[110],"many":[112],"layers":[114],"small":[116],"kernels":[117],"create":[119],"receptive":[121],"field":[122],"more":[124,163],"nonlinearity":[125],"fewer":[127],"parameters":[128],"than":[129],"standard":[130],"configurations.":[131],"When":[132],"combined,":[133],"these":[134],"achieve":[137],"word":[139],"rate":[141,153],"6.2%":[143],"this":[145,148,158,176],"difficult":[146],"task;":[147],"was":[149],"reported":[152],"at":[154],"time":[156],"writing":[159],"even":[162],"remarkable":[164],"given":[165],"human":[167],"itself":[169],"estimated":[171],"4%":[174],"data.":[177]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":4},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}