{"id":"https://openalex.org/W2395342389","doi":"https://doi.org/10.21437/interspeech.2013-455","title":"Deep segmental neural networks for speech recognition","display_name":"Deep segmental neural networks for speech recognition","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2395342389","doi":"https://doi.org/10.21437/interspeech.2013-455","mag":"2395342389"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-455","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5077733105","display_name":"Ossama Abdel\u2010Hamid","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ossama Abdel-Hamid","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671324","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-1014-0790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Deng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101454723","display_name":"Hui Jiang","orcid":"https://orcid.org/0000-0003-4062-7206"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Jiang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077733105"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.8962,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.9763152,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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":0.9979000091552734,"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":0.714381754398346},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6995269060134888},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5889687538146973},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4523155093193054},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4472292363643646},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4278649687767029}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.714381754398346},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6995269060134888},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5889687538146973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4523155093193054},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4472292363643646},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4278649687767029}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2013-455","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.701.7779","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.701.7779","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.yorku.ca/%7Eossama/pub/SegmentalNN.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6800000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1825659173","https://openalex.org/W1981678206","https://openalex.org/W1983628629","https://openalex.org/W1984541135","https://openalex.org/W1993882792","https://openalex.org/W2036242736","https://openalex.org/W2076794394","https://openalex.org/W2083393647","https://openalex.org/W2095168618","https://openalex.org/W2111535841","https://openalex.org/W2131033001","https://openalex.org/W2138530627","https://openalex.org/W2141778357","https://openalex.org/W2147768505","https://openalex.org/W2148632119","https://openalex.org/W2151660570","https://openalex.org/W2155273149","https://openalex.org/W2160815625","https://openalex.org/W2162871885","https://openalex.org/W2226111737","https://openalex.org/W2394932179","https://openalex.org/W2403307209","https://openalex.org/W2569190383"],"related_works":["https://openalex.org/W3175075966","https://openalex.org/W2883762569","https://openalex.org/W1679636228","https://openalex.org/W2329734087","https://openalex.org/W2386387936","https://openalex.org/W2396375857","https://openalex.org/W2156694948","https://openalex.org/W2794558692","https://openalex.org/W3142820373","https://openalex.org/W3176779650"],"abstract_inverted_index":{"Hybrid":[0],"systems":[1,138],"which":[2,103],"integrate":[3],"the":[4,33,37,41,47,51,56,65,79,92,113,116,131,135,145,151],"deep":[5,66],"neural":[6,68],"network":[7,69],"(DNN)":[8],"and":[9,35,123,139,150],"hidden":[10],"Markov":[11],"model":[12,73],"(HMM)":[13],"have":[14],"recently":[15],"achieved":[16],"re-markable":[17],"performance":[18],"in":[19,55,102],"many":[20],"large":[21],"vocabulary":[22],"speech":[23],"recog-nition":[24],"tasks.":[25],"These":[26],"systems,":[27],"however,":[28],"remain":[29],"to":[30,77,94],"rely":[31],"on":[32,108],"HMM":[34],"assume":[36],"acoustic":[38,80],"scores":[39,81],"for":[40],"(windowed)":[42],"frames":[43,104],"are":[44,105],"independent":[45],"given":[46],"state,":[48],"suffering":[49],"from":[50],"same":[52],"difficulty":[53],"as":[54,98,118,120],"previous":[57],"GMM-HMM":[58],"systems.":[59],"In":[60],"this":[61],"pa-per,":[62],"we":[63],"propose":[64],"segmental":[67,72,142,153],"(DSNN),":[70],"a":[71,99],"that":[74,130],"uses":[75],"DNNs":[76],"estimate":[78],"of":[82,115],"phonemic":[83],"or":[84],"sub-phonemic":[85],"segments":[86],"with":[87],"variable":[88],"lengths.":[89],"This":[90],"allows":[91],"DSNN":[93,132],"represent":[95],"each":[96,109],"segment":[97],"single":[100],"unit,":[101],"made":[106],"dependent":[107],"other.":[110],"We":[111],"describe":[112],"architecture":[114],"DSNN,":[117],"well":[119],"its":[121],"learning":[122],"decoding":[124],"algorithms.":[125],"Our":[126],"evaluation":[127],"experiments":[128],"demon-strate":[129],"can":[133],"outperform":[134],"DNN/HMM":[136],"hybrid":[137],"two":[140],"existing":[141],"models":[143],"including":[144],"seg-mental":[146],"conditional":[147],"random":[148],"field":[149],"shallow":[152],"neu-ral":[154],"network.":[155]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}