{"id":"https://openalex.org/W2400684673","doi":"https://doi.org/10.21437/interspeech.2015-246","title":"Sparse coding based features for speech units classification","display_name":"Sparse coding based features for speech units classification","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2400684673","doi":"https://doi.org/10.21437/interspeech.2015-246","mag":"2400684673"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-246","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5101783272","display_name":"Pulkit Sharma","orcid":"https://orcid.org/0000-0001-7870-7098"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pulkit Sharma","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075520691","display_name":"Vinayak Abrol","orcid":"https://orcid.org/0000-0001-8149-8151"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vinayak Abrol","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112944102","display_name":"A. D. Dileep","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A. D. Dileep","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5025998364","display_name":"Anil Kumar Sao","orcid":"https://orcid.org/0000-0001-5316-5528"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anil Kumar Sao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101783272"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1773,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.95789183,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"712","last_page":"715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9940000176429749,"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":0.9940000176429749,"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":0.9914000034332275,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9581000208854675,"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/computer-science","display_name":"Computer science","score":0.7119568586349487},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6540793180465698},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.641229510307312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6064265370368958},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5992616415023804},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.598162055015564},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5365538597106934},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.46940600872039795},{"id":"https://openalex.org/keywords/k-svd","display_name":"K-SVD","score":0.46208783984184265},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4592108726501465},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.44993144273757935},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.4418369233608246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7119568586349487},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6540793180465698},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.641229510307312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6064265370368958},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5992616415023804},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.598162055015564},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5365538597106934},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.46940600872039795},{"id":"https://openalex.org/C154771677","wikidata":"https://www.wikidata.org/wiki/Q17098361","display_name":"K-SVD","level":3,"score":0.46208783984184265},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4592108726501465},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.44993144273757935},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.4418369233608246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-246","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2099321050","https://openalex.org/W2890952311","https://openalex.org/W3134920593","https://openalex.org/W2509955295","https://openalex.org/W2047275718","https://openalex.org/W2034957211","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2388952560","https://openalex.org/W110819671"],"abstract_inverted_index":{"Abstract":[0],"In":[3,17,111],"this":[4,81,112],"work,":[5],"we":[6,83],"propose":[7,84],"sparse":[8],"representation":[9,129],"based":[10,55,177],"features":[11,167],"for":[12,59,130,179],"speech":[13,26,78,116],"units":[14],"classification":[15,181,191,201],"tasks.":[16],"order":[18],"to":[19,41,69,85,101],"effectively":[20,74],"capture":[21],"the":[22,28,37,103,108,159,165],"variations":[23],"in":[24,107,158,196],"a":[25,50,87],"unit,":[27],"proposed":[29,160,166],"method":[30],"employs":[31],"multiple":[32,47],"class":[33,43],"specific":[34],"dictionaries.":[35],"Here,":[36],"training":[38],"data":[39],"belonging":[40],"each":[42,60],"is":[44,57,99,168],"clustered":[45],"into":[46],"clusters,":[48],"and":[49,118,150,199],"principal":[51,71,96],"component":[52],"analysis":[53],"(PCA)":[54],"dictionary":[56,137,153],"learnt":[58],"cluster.":[61],"It":[62],"has":[63],"been":[64],"observed":[65],"that":[66],"coefficients":[67,122],"corresponding":[68],"middle":[70],"components":[72],"can":[73],"discriminate":[75],"among":[76],"different":[77],"units.":[79],"Exploiting":[80],"observation,":[82],"use":[86],"transformation":[88],"function":[89],"known":[90],"as":[91,126,141],"weighted":[92],"decomposition":[93,144],"(WD)":[94],"of":[95,164,182,185,187,192,202],"components,":[97],"which":[98],"used":[100,125],"emphasize":[102],"discriminative":[104],"information":[105],"present":[106],"PCA-based":[109],"dictionary.":[110],"paper,":[113],"both":[114],"raw":[115],"samples":[117],"mel":[119],"frequency":[120],"cepstral":[121],"(MFCC)":[123],"are":[124,155],"an":[127],"initial":[128],"feature":[131],"extraction.":[132],"For":[133],"comparison,":[134],"various":[135],"popular":[136],"learning":[138],"techniques":[139],"such":[140],"K-singular":[142],"value":[143],"(KSVD),":[145],"simultaneous":[146],"codeword":[147],"optimization":[148],"(SimCO)":[149],"greedy":[151],"adaptive":[152],"(GAD)":[154],"also":[156],"employed":[157],"framework.":[161],"The":[162],"effectiveness":[163],"demonstrated":[169],"using":[170],"continuous":[171],"density":[172],"hidden":[173],"Markov":[174],"model":[175],"(CDHMM)":[176],"classifiers":[178],"(i)":[180],"isolated":[183],"utterances":[184],"E-set":[186],"English":[188],"alphabet,":[189],"(ii)":[190],"consonant-vowel":[193],"(CV)":[194],"segments":[195],"Hindi":[197],"language":[198],"(iii)":[200],"phoneme":[203],"from":[204],"TIMIT":[205],"phonetic":[206],"corpus.":[207]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}