{"id":"https://openalex.org/W2067474491","doi":"https://doi.org/10.1109/icassp.2010.5495649","title":"Sparse coding for speech recognition","display_name":"Sparse coding for speech recognition","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2067474491","doi":"https://doi.org/10.1109/icassp.2010.5495649","mag":"2067474491"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 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/A5109860004","display_name":"G. S. V. S. Sivaram","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"G.S.V.S. Sivaram","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, US","Department of Electrical and Computer Engineering, Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, US","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080686450","display_name":"Sridhar Krishna Nemala","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sridhar Krishna Nemala","raw_affiliation_strings":["Department of Electrical & Computer Engineering, Johns Hopkins University, USA","Department of Electrical and Computer Engineering, Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038788686","display_name":"Mounya Elhilali","orcid":"https://orcid.org/0000-0003-2597-738X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mounya Elhilali","raw_affiliation_strings":["Department of Electrical & Computer Engineering, Johns Hopkins University, USA","Department of Electrical and Computer Engineering, Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101413113","display_name":"Trac D. Tran","orcid":"https://orcid.org/0000-0002-0421-8416"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trac D. Tran","raw_affiliation_strings":["Department of Electrical & Computer Engineering, Johns Hopkins University, USA","Department of Electrical and Computer Engineering, Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042260050","display_name":"Hynek He\u0159mansk\u00fd","orcid":"https://orcid.org/0000-0001-8032-4811"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hynek Hermansky","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, US","Department of Electrical and Computer Engineering, Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, US","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5109860004"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":9.9179,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.98682171,"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":"4346","last_page":"4349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T11447","display_name":"Blind Source Separation Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7532778978347778},{"id":"https://openalex.org/keywords/neural-coding","display_name":"Neural coding","score":0.7399492859840393},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6738955974578857},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5525453686714172},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.547902524471283},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5475382804870605},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.5329478979110718},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5107626914978027},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5102636814117432},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5086827874183655},{"id":"https://openalex.org/keywords/basis-function","display_name":"Basis function","score":0.48683542013168335},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.47342994809150696},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4370183050632477},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.156112402677536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7532778978347778},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.7399492859840393},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6738955974578857},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5525453686714172},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.547902524471283},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5475382804870605},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.5329478979110718},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5107626914978027},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5102636814117432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5086827874183655},{"id":"https://openalex.org/C5917680","wikidata":"https://www.wikidata.org/wiki/Q2621825","display_name":"Basis function","level":2,"score":0.48683542013168335},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.47342994809150696},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4370183050632477},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.156112402677536},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2010.5495649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.221.2838","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.221.2838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://thanglong.ece.jhu.edu/Tran/Pub/Sparse_Coding_Speech_Recognition_ICASSP2010.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W130921173","https://openalex.org/W185597827","https://openalex.org/W203051973","https://openalex.org/W811578723","https://openalex.org/W1553004968","https://openalex.org/W1980501707","https://openalex.org/W2071489795","https://openalex.org/W2077804127","https://openalex.org/W2105464873","https://openalex.org/W2119667497","https://openalex.org/W2145889472","https://openalex.org/W2156293100","https://openalex.org/W2296616510","https://openalex.org/W4250955649"],"related_works":["https://openalex.org/W2890544631","https://openalex.org/W2067062989","https://openalex.org/W2998105788","https://openalex.org/W4205656132","https://openalex.org/W2363301696","https://openalex.org/W2111634407","https://openalex.org/W3004790527","https://openalex.org/W2203155458","https://openalex.org/W2783282829","https://openalex.org/W2352223112"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,23,29,60,73],"novel":[4],"feature":[5],"extraction":[6],"technique":[7],"for":[8,55],"speech":[9,27],"recognition":[10,108],"based":[11],"on":[12],"the":[13,41,44,68,80,85,94,100,112,116],"principles":[14,103],"of":[15,26,32,36,43,62,87,104],"sparse":[16],"coding.":[17],"The":[18],"idea":[19],"is":[20],"to":[21],"express":[22],"spectro-temporal":[24],"pattern":[25],"as":[28],"linear":[30,45],"combination":[31,46],"an":[33],"overcomplete":[34,63],"set":[35,61,70],"basis":[37,64,96],"functions":[38,65,97],"such":[39],"that":[40,111],"weights":[42,50],"are":[47,52,91],"sparse.":[48],"These":[49],"(features)":[51],"subsequently":[53],"used":[54],"acoustic":[56],"modeling.":[57],"We":[58],"learn":[59],"(dictionary)":[66],"from":[67],"training":[69],"by":[71,98],"adopting":[72],"previously":[74],"proposed":[75,113],"algorithm":[76],"which":[77],"iteratively":[78],"minimizes":[79],"reconstruction":[81],"error":[82],"and":[83,122],"maximizes":[84],"sparsity":[86],"weights.":[88],"Furthermore,":[89],"features":[90,114,118],"derived":[92],"using":[93],"learned":[95],"applying":[99],"well":[101],"established":[102],"compressive":[105],"sensing.":[106],"Phoneme":[107],"experiments":[109],"show":[110],"outperform":[115],"conventional":[117],"in":[119],"both":[120],"clean":[121],"noisy":[123],"conditions.":[124]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
