{"id":"https://openalex.org/W2141190215","doi":"https://doi.org/10.1109/icassp.2013.6638083","title":"Tandem HMM with convolutional neural network for handwritten word recognition","display_name":"Tandem HMM with convolutional neural network for handwritten word recognition","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2141190215","doi":"https://doi.org/10.1109/icassp.2013.6638083","mag":"2141190215"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638083","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/A5030191869","display_name":"Th\u00e9odore Bluche","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Theodore Bluche","raw_affiliation_strings":["A2iA SA, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A2iA SA, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["Laboratoire d'Informatique pour la Mecanique et les Sciences de l'Ingenieur, Orsay, \u00c3\u017dle-de-France, FR","Spoken Language Process. Group, LIMSI, Orsay, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique pour la Mecanique et les Sciences de l'Ingenieur, Orsay, \u00c3\u017dle-de-France, FR","institution_ids":["https://openalex.org/I4210115485"]},{"raw_affiliation_string":"Spoken Language Process. Group, LIMSI, Orsay, France","institution_ids":["https://openalex.org/I4210115485"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024834377","display_name":"Christopher Kermorvant","orcid":"https://orcid.org/0000-0002-7508-4080"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christopher Kermorvant","raw_affiliation_strings":["A2iA SA, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A2iA SA, France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0389,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.92811101,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2390","last_page":"2394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.9393342733383179},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8174495697021484},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7241816520690918},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6642791628837585},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6470752954483032},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6450393199920654},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.532634973526001},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5084878206253052},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4881792664527893},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45994043350219727},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.44510316848754883},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44478002190589905},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07811734080314636},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.062021851539611816}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9393342733383179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8174495697021484},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7241816520690918},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6642791628837585},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6470752954483032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6450393199920654},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.532634973526001},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5084878206253052},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4881792664527893},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45994043350219727},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.44510316848754883},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44478002190589905},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07811734080314636},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.062021851539611816},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6638083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638083","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W811578723","https://openalex.org/W1524333225","https://openalex.org/W1995574284","https://openalex.org/W2012897754","https://openalex.org/W2015861736","https://openalex.org/W2033154814","https://openalex.org/W2061994628","https://openalex.org/W2084859622","https://openalex.org/W2099070536","https://openalex.org/W2106986062","https://openalex.org/W2112796928","https://openalex.org/W2131850988","https://openalex.org/W2147220807","https://openalex.org/W2147768505","https://openalex.org/W2148695089","https://openalex.org/W2152928267","https://openalex.org/W2165712214","https://openalex.org/W2168504305","https://openalex.org/W2474855605","https://openalex.org/W6631362777","https://openalex.org/W6653316155","https://openalex.org/W6682050888","https://openalex.org/W6684249834","https://openalex.org/W6721014087"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W1980930823","https://openalex.org/W2148167314","https://openalex.org/W2401522294","https://openalex.org/W1962828410","https://openalex.org/W2253780618","https://openalex.org/W4205429340","https://openalex.org/W4232239836","https://openalex.org/W2079838398"],"abstract_inverted_index":{"In":[0,36],"this":[1,37],"paper,":[2],"we":[3,39,95],"investigate":[4],"the":[5,87,127],"combination":[6],"of":[7],"hidden":[8,52],"Markov":[9,53],"models":[10,54],"and":[11,94,101],"convolutional":[12,20],"neural":[13,21,123],"networks":[14,22],"for":[15,62],"handwritten":[16,33],"word":[17],"recognition.":[18,35],"The":[19,70,115],"have":[23],"been":[24],"successfully":[25],"applied":[26],"to":[27,47,98,107,121],"various":[28],"computer":[29],"vision":[30],"tasks,":[31],"including":[32],"character":[34],"work,":[38],"show":[40],"that":[41],"they":[42],"can":[43],"replace":[44],"Gaussian":[45,65,109],"mixtures":[46],"compute":[48],"emission":[49],"probabilities":[50],"in":[51],"(hybrid":[55],"combination),":[56],"or":[57,82],"serve":[58],"as":[59],"feature":[60],"extractor":[61],"a":[63,74,108],"standard":[64],"HMM":[66,76,110],"system":[67],"(tandem":[68],"combination).":[69],"proposed":[71],"systems":[72,117,129],"outperform":[73],"basic":[75],"based":[77,111],"on":[78,89,112],"either":[79],"decorrelated":[80],"pixels":[81],"handcrafted":[83],"features.":[84],"We":[85],"validated":[86],"approach":[88],"two":[90],"publicly":[91],"available":[92],"databases,":[93],"report":[96],"up":[97],"60%":[99],"(Rimes)":[100],"35%":[102],"(IAM)":[103],"relative":[104],"improvement":[105],"compared":[106],"pixel":[113],"values.":[114],"final":[116],"give":[118],"comparable":[119],"results":[120],"recurrent":[122],"networks,":[124],"which":[125],"are":[126],"best":[128],"since":[130],"2009.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":8},{"year":2014,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}