{"id":"https://openalex.org/W2155273149","doi":"https://doi.org/10.1109/icassp.2012.6288864","title":"Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition","display_name":"Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2155273149","doi":"https://doi.org/10.1109/icassp.2012.6288864","mag":"2155273149"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5077733105","display_name":"Ossama Abdel\u2010Hamid","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ossama Abdel-Hamid","raw_affiliation_strings":["Department of Computer Science and Engineering, York University, Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103742478","display_name":"Abdelrahman Mohamed","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abdel-rahman Mohamed","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101454723","display_name":"Hui Jiang","orcid":"https://orcid.org/0000-0003-4062-7206"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hui Jiang","raw_affiliation_strings":["Department of Computer Science and Engineering, York University, Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052428595","display_name":"Gerald Penn","orcid":"https://orcid.org/0000-0003-3553-8305"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gerald Penn","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":895,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4277","last_page":"4280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9962999820709229,"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/T11309","display_name":"Music and Audio Processing","score":0.9944999814033508,"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/timit","display_name":"TIMIT","score":0.9213277697563171},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8170071244239807},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.755574643611908},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.691544771194458},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6628395318984985},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6345171928405762},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5977266430854797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5502554774284363},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42800551652908325}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.9213277697563171},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8170071244239807},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.755574643611908},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.691544771194458},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6628395318984985},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6345171928405762},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5977266430854797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5502554774284363},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42800551652908325}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6288864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.224.2749","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.224.2749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.toronto.edu/%7Easamir/papers/icassp12_cnn.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1538131130","https://openalex.org/W1993882792","https://openalex.org/W2002342963","https://openalex.org/W2076794394","https://openalex.org/W2077804127","https://openalex.org/W2103359087","https://openalex.org/W2107789863","https://openalex.org/W2112796928","https://openalex.org/W2134557905","https://openalex.org/W2144792281","https://openalex.org/W2394932179","https://openalex.org/W2504108613","https://openalex.org/W6632100814","https://openalex.org/W6675321185","https://openalex.org/W6676071220"],"related_works":["https://openalex.org/W4401096132","https://openalex.org/W2136763963","https://openalex.org/W3134920593","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2071828724","https://openalex.org/W1909151225","https://openalex.org/W1987783679"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNN)":[3],"have":[4],"showed":[5],"success":[6,17],"in":[7,29,59,111,139],"achieving":[8],"translation":[9],"invariance":[10],"for":[11],"many":[12],"image":[13],"processing":[14],"tasks.":[15],"The":[16],"is":[18,85,109,173],"largely":[19],"attributed":[20],"to":[21,38,41,53,62,66,95],"the":[22,30,45,88,105,119,128,140,152,165,169,180],"use":[23,54,186],"of":[24,47,78,91,99,155,168],"local":[25,55,79],"filtering":[26,56,80],"and":[27,57,82,158],"max-pooling":[28,58,83],"CNN":[31,40,107,130,171],"architecture.":[32],"In":[33,73,102],"this":[34],"paper,":[35],"we":[36],"propose":[37,52],"apply":[39],"speech":[42,70,100,115],"recognition":[43,71,116],"within":[44],"framework":[46],"hybrid":[48],"NN-HMM":[49],"model.":[50,191],"We":[51],"frequency":[60],"domain":[61],"normalize":[63,96],"speaker":[64,113],"variance":[65],"achieve":[67,133],"higher":[68],"multi-speaker":[69],"performance.":[72],"our":[74,103],"method,":[75],"a":[76,112,148,187],"pair":[77],"layer":[81,84],"added":[86],"at":[87],"lowest":[89],"end":[90],"neural":[92],"network":[93],"(NN)":[94],"spectral":[97],"variations":[98],"signals.":[101],"experiments,":[104],"proposed":[106,129,170],"architecture":[108],"evaluated":[110],"independent":[114],"task":[117],"using":[118,151],"standard":[120],"TIMIT":[121,142,182],"data":[122],"sets.":[123],"Experimental":[124],"results":[125,161,178],"show":[126,163],"that":[127,164,185],"method":[131],"can":[132],"over":[134],"10%":[135],"relative":[136],"error":[137],"reduction":[138],"core":[141],"test":[143,183],"sets":[144,184],"when":[145],"comparing":[146],"with":[147],"regular":[149],"NN":[150,190],"same":[153,181],"number":[154],"hidden":[156],"layers":[157],"weights.":[159],"Our":[160],"also":[162],"best":[166],"result":[167],"model":[172],"better":[174],"than":[175],"previously":[176],"published":[177],"on":[179],"pre-trained":[188],"deep":[189]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":38},{"year":2022,"cited_by_count":41},{"year":2021,"cited_by_count":85},{"year":2020,"cited_by_count":103},{"year":2019,"cited_by_count":104},{"year":2018,"cited_by_count":100},{"year":2017,"cited_by_count":101},{"year":2016,"cited_by_count":101},{"year":2015,"cited_by_count":79},{"year":2014,"cited_by_count":58},{"year":2013,"cited_by_count":25},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}