{"id":"https://openalex.org/W2906816730","doi":"https://doi.org/10.1109/icapr.2017.8593158","title":"Robust representation and efficient matching of spoken word templates","display_name":"Robust representation and efficient matching of spoken word templates","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2906816730","doi":"https://doi.org/10.1109/icapr.2017.8593158","mag":"2906816730"},"language":"en","primary_location":{"id":"doi:10.1109/icapr.2017.8593158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icapr.2017.8593158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Ninth International Conference on Advances in Pattern Recognition (ICAPR)","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/A5101251253","display_name":"Anupam Mandal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]},{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Anupam Mandal","raw_affiliation_strings":["Center for AI & Robotics, Bangalore, 560093, India","Center for AI & Robotics, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Center for AI & Robotics, Bangalore, 560093, India","institution_ids":["https://openalex.org/I4210121405"]},{"raw_affiliation_string":"Center for AI & Robotics, Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029696356","display_name":"K. R. Prasanna Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]},{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K.R. Prasanna Kumar","raw_affiliation_strings":["Center for AI & Robotics, Bangalore, 560093, India","Center for AI & Robotics, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Center for AI & Robotics, Bangalore, 560093, India","institution_ids":["https://openalex.org/I4210121405"]},{"raw_affiliation_string":"Center for AI & Robotics, Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032809289","display_name":"Pabitra Mitra","orcid":"https://orcid.org/0000-0002-1908-9813"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pabitra Mitra","raw_affiliation_strings":["IIT Kharagpur, Department of CSE, Kharagpur, 731302, India","Department of CSE, IIT Kharagpur, Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"IIT Kharagpur, Department of CSE, Kharagpur, 731302, India","institution_ids":["https://openalex.org/I145894827"]},{"raw_affiliation_string":"Department of CSE, IIT Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101251253"],"corresponding_institution_ids":["https://openalex.org/I181514455","https://openalex.org/I4210121405"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25407826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9975000023841858,"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":0.9975000023841858,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9958000183105469,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9945999979972839,"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/robustness","display_name":"Robustness (evolution)","score":0.8256876468658447},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7703851461410522},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.6944246888160706},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6778600215911865},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6705760359764099},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6684120297431946},{"id":"https://openalex.org/keywords/template-matching","display_name":"Template matching","score":0.646460235118866},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.6045553088188171},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5568813681602478},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43901559710502625}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8256876468658447},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7703851461410522},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.6944246888160706},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6778600215911865},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6705760359764099},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6684120297431946},{"id":"https://openalex.org/C158096908","wikidata":"https://www.wikidata.org/wiki/Q3983303","display_name":"Template matching","level":3,"score":0.646460235118866},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.6045553088188171},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5568813681602478},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43901559710502625},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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":1,"locations":[{"id":"doi:10.1109/icapr.2017.8593158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icapr.2017.8593158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Ninth International Conference on Advances in Pattern Recognition (ICAPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1815792","https://openalex.org/W1973749706","https://openalex.org/W1975126845","https://openalex.org/W1999999865","https://openalex.org/W2020498246","https://openalex.org/W2059652594","https://openalex.org/W2110625382","https://openalex.org/W2126203737","https://openalex.org/W2128160875","https://openalex.org/W2145065594","https://openalex.org/W2403207842"],"related_works":["https://openalex.org/W2335896301","https://openalex.org/W2012393389","https://openalex.org/W2333240621","https://openalex.org/W3006618853","https://openalex.org/W2253066076","https://openalex.org/W2295636786","https://openalex.org/W2399492946","https://openalex.org/W2361315595","https://openalex.org/W2578092491","https://openalex.org/W3184620678"],"abstract_inverted_index":{"Two":[0],"important":[1],"considerations":[2],"in":[3,58,76,94,143,172,202,207],"template":[4,30,72],"based":[5,34,114,180,222],"speech":[6],"recognition":[7,23,48,79,147,173,213,243],"are":[8,108,162],"i)":[9],"achieving":[10],"robustness":[11,68,186],"of":[12,24,38,43,69,78,90,96,112,141,145,178,187,220,245,252],"the":[13,39,70,97,183,188,203,225,242,246],"templates":[14,57,113,161,201],"to":[15,176],"speaker":[16],"and":[17,20,83,149,198],"environmental":[18],"variations,":[19],"ii)":[21],"fast":[22],"templates.":[25,254],"In":[26],"this":[27],"paper,":[28],"a":[29,44,103,155,169,229],"representation":[31,73,166,181,223],"is":[32,49,74,92,129,192,232],"proposed":[33,71,136,165,247],"on":[35,81,115],"spectral":[36],"peaks":[37],"mel-scale":[40],"magnitude":[41],"spectrogram":[42],"spoken":[45,86],"word.":[46],"The":[47,67,88,106,238],"performed":[50],"by":[51,235,249],"finding":[52],"k-":[53],"closest":[54],"matching":[55,91,102],"representative":[56,200],"an":[59,139],"index":[60,205],"built":[61],"using":[62],"locality":[63],"sensitive":[64],"hashing":[65],"(LSH).":[66],"studied":[75],"terms":[77,95],"accuracy":[80,214],"clean":[82,133,197],"noisy":[84,199,216],"isolated":[85],"words.":[87],"efficiency":[89],"measured":[93],"average":[98],"time":[99,123,153,226],"taken":[100,227],"for":[101,126,154,228],"test":[104],"template.":[105],"results":[107,206],"compared":[109,175],"with":[110,121],"those":[111],"Mel":[116],"frequency":[117],"Cepstral":[118],"coefficients":[119],"(MFCC)":[120],"dynamic":[122],"warping":[124],"(DTW)":[125],"matching.":[127],"It":[128],"found":[130],"that":[131,177,194,219],"under":[132,215],"conditions":[134,217],"our":[135],"approach":[137],"shows":[138,168],"improvement":[140],"2.4%":[142],"case":[144],"1-best":[146,212],"performance":[148,174,244],"8.7":[150],"times":[151,210],"less":[152],"match":[156,231],"when":[157],"all":[158],"available":[159],"training":[160,253],"used.":[163],"Our":[164],"also":[167,240],"smoother":[170],"fall":[171],"MFCC":[179,221],"indicating":[182],"better":[184],"noise":[185],"former.":[189],"Further,":[190],"it":[191],"demonstrated":[193],"including":[195],"both":[196],"LSH":[204],"almost":[208],"3":[209],"higher":[211],"than":[218],"while":[224],"single":[230],"still":[233],"lower":[234],"5.8":[236],"times.":[237],"paper":[239],"studies":[241],"method":[248],"varying":[250],"number":[251]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}