{"id":"https://openalex.org/W2075925017","doi":"https://doi.org/10.1109/icassp.2014.6854926","title":"Sequence classification using the high-level features extracted from deep neural networks","display_name":"Sequence classification using the high-level features extracted from deep neural networks","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2075925017","doi":"https://doi.org/10.1109/icassp.2014.6854926","mag":"2075925017"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854926","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/A5100671324","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-1014-0790"},"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":true,"raw_author_name":"Li Deng","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/A5088339142","display_name":"Jianshu Chen","orcid":"https://orcid.org/0000-0001-8216-2756"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianshu Chen","raw_affiliation_strings":["University of California, Los Angeles, CA, USA","University of California\u2014Los Angeles Los Angeles CA USA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California\u2014Los Angeles Los Angeles CA USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100671324"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":11.0328,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.98409308,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6844","last_page":"6848"},"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":0.9998000264167786,"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":0.9994000196456909,"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":0.7480369806289673},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.717657744884491},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6039206385612488},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5877416133880615},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5822324156761169},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5611149668693542},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5159193277359009},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5017573833465576},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4932054877281189},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4900888204574585},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48294442892074585},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4681048095226288},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.46405401825904846},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4536336362361908},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4483701288700104},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.43864524364471436},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4332394599914551},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09530076384544373}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480369806289673},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.717657744884491},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6039206385612488},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5877416133880615},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5822324156761169},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5611149668693542},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5159193277359009},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5017573833465576},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4932054877281189},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4900888204574585},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48294442892074585},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4681048095226288},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.46405401825904846},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4536336362361908},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4483701288700104},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.43864524364471436},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4332394599914551},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09530076384544373},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"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/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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854926","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W217970951","https://openalex.org/W1269046860","https://openalex.org/W1553004968","https://openalex.org/W1815076433","https://openalex.org/W1984541135","https://openalex.org/W1987238397","https://openalex.org/W1990351874","https://openalex.org/W1993882792","https://openalex.org/W2005708641","https://openalex.org/W2012897754","https://openalex.org/W2022011789","https://openalex.org/W2036242736","https://openalex.org/W2071310251","https://openalex.org/W2091432990","https://openalex.org/W2095168618","https://openalex.org/W2100729928","https://openalex.org/W2100966557","https://openalex.org/W2105099419","https://openalex.org/W2108563286","https://openalex.org/W2108597378","https://openalex.org/W2125964738","https://openalex.org/W2131342762","https://openalex.org/W2133282586","https://openalex.org/W2139622435","https://openalex.org/W2141778357","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2149600041","https://openalex.org/W2160815625","https://openalex.org/W2161742217","https://openalex.org/W2165712214","https://openalex.org/W2168013545","https://openalex.org/W2184045248","https://openalex.org/W2296748324","https://openalex.org/W2394932179","https://openalex.org/W2400691855","https://openalex.org/W2400718301","https://openalex.org/W2403195671","https://openalex.org/W3181208372","https://openalex.org/W6608710415","https://openalex.org/W6638545294","https://openalex.org/W6675184043","https://openalex.org/W6679429981","https://openalex.org/W6679700082","https://openalex.org/W6697318756","https://openalex.org/W6712963495"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2294335174","https://openalex.org/W2025614924","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W2073996508","https://openalex.org/W2053269318","https://openalex.org/W2546021431","https://openalex.org/W2581127593"],"abstract_inverted_index":{"The":[0,133,167],"recent":[1,81],"success":[2],"of":[3,23,42,65,75,86,90,120,130,146,162,183],"deep":[4],"neural":[5,165],"networks":[6],"(DNNs)":[7],"in":[8,59,106,187],"speech":[9],"recognition":[10,35],"can":[11],"be":[12],"attributed":[13],"largely":[14],"to":[15,18,117,122],"their":[16],"ability":[17],"extract":[19],"a":[20,87,163],"specific":[21],"form":[22],"high-level":[24],"features":[25,57,113,139],"from":[26,97,102,141,171],"raw":[27],"acoustic":[28],"data":[29],"for":[30,152,157],"subsequent":[31],"sequence":[32,67,127],"classification":[33,128],"or":[34],"tasks.":[36],"Among":[37],"the":[38,62,73,84,94,98,107,115,125,138,142,147,150,158,172,184,188,191],"many":[39],"possible":[40],"forms":[41,46],"DNN":[43,56,91,148,189],"features,":[44,92],"what":[45],"are":[47,58,72],"more":[48],"useful":[49],"than":[50,181],"others":[51],"and":[52,71,101],"how":[53],"effective":[54],"these":[55,112],"connection":[60],"with":[61],"different":[63],"types":[64,119],"downstream":[66],"recognizers":[68],"remained":[69],"unexplored":[70],"focus":[74],"this":[76],"paper.":[77],"We":[78,109],"report":[79],"our":[80],"work":[82],"on":[83],"construction":[85],"diverse":[88],"set":[89],"including":[93],"vectors":[95],"extracted":[96],"output":[99,174],"layer":[100,145,175],"various":[103],"hidden":[104,144,185],"layers":[105,186],"DNN.":[108],"then":[110],"apply":[111],"as":[114],"inputs":[116],"four":[118,154],"classifiers":[121],"carry":[123],"out":[124],"identical":[126],"task":[129],"phone":[131],"recognition.":[132],"experimental":[134],"results":[135],"show":[136],"that":[137],"derived":[140,170],"top":[143,192],"perform":[149],"best":[151],"all":[153],"classifiers,":[155],"especially":[156],"autoregressive-moving-average":[159],"(ARMA)":[160],"version":[161],"recurrent":[164],"network.":[166],"feature":[168],"vector":[169],"DNN's":[173],"performs":[176],"slightly":[177],"worse":[178],"but":[179],"better":[180],"any":[182],"except":[190],"one.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":5}],"updated_date":"2026-03-31T07:56:22.981413","created_date":"2025-10-10T00:00:00"}