{"id":"https://openalex.org/W2075449699","doi":"https://doi.org/10.1109/icassp.2014.6854638","title":"Phone sequence modeling with recurrent neural networks","display_name":"Phone sequence modeling with recurrent neural networks","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2075449699","doi":"https://doi.org/10.1109/icassp.2014.6854638","mag":"2075449699"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854638","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/A5037330846","display_name":"Nicolas Boulanger-Lewandowski","orcid":null},"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":true,"raw_author_name":"Nicolas Boulanger-Lewandowski","raw_affiliation_strings":["Department IRO, Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, QC, Canada","Dept. IRO Montreal, Univ. de Montreal, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Department IRO, Universit\u00e9 de Montr\u00e9al, Montr\u00e9al, QC, Canada","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"Dept. IRO Montreal, Univ. de Montreal, Montreal, QC, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012153296","display_name":"Jasha Droppo","orcid":"https://orcid.org/0000-0001-6097-0090"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jasha Droppo","raw_affiliation_strings":["Microsoft Research, One Microsoft Way, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research,Redmond,WA,USA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113773386","display_name":"Mike Seltzer","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mike Seltzer","raw_affiliation_strings":["Microsoft Research, One Microsoft Way, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research,Redmond,WA,USA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Microsoft Research, One Microsoft Way, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research,Redmond,WA,USA]","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5037330846"],"corresponding_institution_ids":["https://openalex.org/I70931966"],"apc_list":null,"apc_paid":null,"fwci":4.4991,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.94837599,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"29","issue":null,"first_page":"5417","last_page":"5421"},"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":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.8450583219528198},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7424324750900269},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7010853290557861},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6987228989601135},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6527845859527588},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6165871024131775},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5695861577987671},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5220246911048889},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.516646683216095},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.49919676780700684},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.49892497062683105},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.48598799109458923},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4770485758781433},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.476445734500885},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.4327344298362732},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3819095492362976},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2849087119102478},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13926565647125244}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8450583219528198},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7424324750900269},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7010853290557861},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6987228989601135},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6527845859527588},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6165871024131775},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5695861577987671},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5220246911048889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.516646683216095},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.49919676780700684},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.49892497062683105},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.48598799109458923},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4770485758781433},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.476445734500885},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.4327344298362732},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3819095492362976},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2849087119102478},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13926565647125244},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854638","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1538748823","https://openalex.org/W1819710477","https://openalex.org/W1828163288","https://openalex.org/W1934019294","https://openalex.org/W2062227835","https://openalex.org/W2084514013","https://openalex.org/W2107878631","https://openalex.org/W2108563286","https://openalex.org/W2127141656","https://openalex.org/W2141778357","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2147880316","https://openalex.org/W2160815625","https://openalex.org/W2162911105","https://openalex.org/W2184045248","https://openalex.org/W2185726469","https://openalex.org/W2395935897","https://openalex.org/W2766736793","https://openalex.org/W2962968839","https://openalex.org/W6638749077","https://openalex.org/W6640267182","https://openalex.org/W6682082992","https://openalex.org/W6682610290"],"related_works":["https://openalex.org/W2994894110","https://openalex.org/W4377862891","https://openalex.org/W2005708641","https://openalex.org/W1566315437","https://openalex.org/W2151348424","https://openalex.org/W2080458333","https://openalex.org/W4221142855","https://openalex.org/W2050397613","https://openalex.org/W2244609359","https://openalex.org/W2141404479"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,35],"investigate":[4],"phone":[5,82],"sequence":[6,43],"modeling":[7],"with":[8,28],"recurrent":[9],"neural":[10,66],"networks":[11],"in":[12,59,81,86,98],"the":[13,47,54],"context":[14],"of":[15,49,79],"speech":[16],"recognition.":[17],"We":[18,45],"introduce":[19],"a":[20,25,62,72],"hybrid":[21],"architecture":[22],"that":[23,91],"combines":[24],"phonetic":[26,51],"model":[27,33,52],"an":[29],"arbitrary":[30],"frame-level":[31],"acoustic":[32,69],"and":[34,42,56,71,84],"propose":[36],"efficient":[37],"algorithms":[38],"for":[39],"training,":[40],"decoding":[41],"alignment.":[44],"evaluate":[46],"advantage":[48],"our":[50,92],"on":[53],"TIMIT":[55],"Switchboard-mini":[57],"datasets":[58],"complementarity":[60],"to":[61],"powerful":[63],"context-dependent":[64],"deep":[65],"network":[67],"(DNN)":[68],"classifier":[70],"higher-level":[73],"3-gram":[74],"language":[75],"model.":[76],"Consistent":[77],"improvements":[78],"2-10%":[80],"accuracy":[83],"3%":[85],"word":[87],"error":[88],"rate":[89],"suggest":[90],"approach":[93],"can":[94],"readily":[95],"replace":[96],"HMMs":[97],"current":[99],"state-of-the-art":[100],"systems.":[101]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}