{"id":"https://openalex.org/W1998766338","doi":"https://doi.org/10.1109/taslp.2014.2311322","title":"Query-by-Example Spoken Term Detection using Frequency Domain Linear Prediction and Non-Segmental Dynamic Time Warping","display_name":"Query-by-Example Spoken Term Detection using Frequency Domain Linear Prediction and Non-Segmental Dynamic Time Warping","publication_year":2014,"publication_date":"2014-03-11","ids":{"openalex":"https://openalex.org/W1998766338","doi":"https://doi.org/10.1109/taslp.2014.2311322","mag":"1998766338"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2014.2311322","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2311322","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5061686905","display_name":"Gautam Mantena","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]},{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]},{"id":"https://openalex.org/I4210097016","display_name":"International Institute of Information Technology","ror":"https://ror.org/00qryer39","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210097016"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Gautam Mantena","raw_affiliation_strings":["International Institute of Information Technology (IIIT-H), Gachibowli, Hyderabad, India","[International Institute of Information Technology Hyderabad, India]"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology (IIIT-H), Gachibowli, Hyderabad, India","institution_ids":["https://openalex.org/I4210097016","https://openalex.org/I65181880"]},{"raw_affiliation_string":"[International Institute of Information Technology Hyderabad, India]","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086878243","display_name":"Sivanand Achanta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210097016","display_name":"International Institute of Information Technology","ror":"https://ror.org/00qryer39","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210097016"]},{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]},{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sivanand Achanta","raw_affiliation_strings":["International Institute of Information Technology (IIIT-H), Gachibowli, Hyderabad, India","[International Institute of Information Technology Hyderabad, India]"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology (IIIT-H), Gachibowli, Hyderabad, India","institution_ids":["https://openalex.org/I4210097016","https://openalex.org/I65181880"]},{"raw_affiliation_string":"[International Institute of Information Technology Hyderabad, India]","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113522207","display_name":"Kishore Prahallad","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]},{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]},{"id":"https://openalex.org/I4210097016","display_name":"International Institute of Information Technology","ror":"https://ror.org/00qryer39","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210097016"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kishore Prahallad","raw_affiliation_strings":["International Institute of Information Technology (IIIT-H), Gachibowli, Hyderabad, India","[International Institute of Information Technology Hyderabad, India]"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology (IIIT-H), Gachibowli, Hyderabad, India","institution_ids":["https://openalex.org/I4210097016","https://openalex.org/I65181880"]},{"raw_affiliation_string":"[International Institute of Information Technology Hyderabad, India]","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061686905"],"corresponding_institution_ids":["https://openalex.org/I4210097016","https://openalex.org/I64189192","https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":7.5694,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.97887731,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"22","issue":"5","first_page":"946","last_page":"955"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9980999827384949,"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/dynamic-time-warping","display_name":"Dynamic time warping","score":0.9322319030761719},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8049366474151611},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7102985382080078},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6910471320152283},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.49815893173217773},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4919581115245819},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.4897348880767822},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4742395281791687},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.444735050201416},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43303295969963074},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.42516767978668213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41652268171310425},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.32144153118133545},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.10493946075439453},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.099585622549057},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.07371005415916443}],"concepts":[{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.9322319030761719},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8049366474151611},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7102985382080078},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6910471320152283},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.49815893173217773},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4919581115245819},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.4897348880767822},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4742395281791687},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.444735050201416},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43303295969963074},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.42516767978668213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41652268171310425},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32144153118133545},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.10493946075439453},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.099585622549057},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.07371005415916443},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2014.2311322","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2311322","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1815792","https://openalex.org/W2533495","https://openalex.org/W49437105","https://openalex.org/W99283740","https://openalex.org/W114193738","https://openalex.org/W170732776","https://openalex.org/W1490960657","https://openalex.org/W1885478233","https://openalex.org/W1966264494","https://openalex.org/W1974745151","https://openalex.org/W2056786202","https://openalex.org/W2057007397","https://openalex.org/W2068349492","https://openalex.org/W2090861223","https://openalex.org/W2100580843","https://openalex.org/W2108776455","https://openalex.org/W2113932204","https://openalex.org/W2114478143","https://openalex.org/W2126203737","https://openalex.org/W2128160875","https://openalex.org/W2137089646","https://openalex.org/W2144994235","https://openalex.org/W2145880678","https://openalex.org/W2147676440","https://openalex.org/W2164365067","https://openalex.org/W2166778951","https://openalex.org/W2168080440","https://openalex.org/W2295061986","https://openalex.org/W2395865585","https://openalex.org/W2401464865","https://openalex.org/W2442329935","https://openalex.org/W6600088033","https://openalex.org/W6602023532","https://openalex.org/W6604666349","https://openalex.org/W6629386585","https://openalex.org/W6697187339","https://openalex.org/W6718561954"],"related_works":["https://openalex.org/W2335896301","https://openalex.org/W2012393389","https://openalex.org/W2333240621","https://openalex.org/W2137764249","https://openalex.org/W3006618853","https://openalex.org/W2253066076","https://openalex.org/W2295636786","https://openalex.org/W2399492946","https://openalex.org/W2578092491","https://openalex.org/W2908089434"],"abstract_inverted_index":{"The":[0,89],"task":[1],"of":[2,28,52,67,74,85,104,138,155],"query-by-example":[3],"spoken":[4,12,15],"term":[5],"detection":[6],"(QbE-STD)":[7],"is":[8,168,175],"to":[9,57,114],"find":[10],"a":[11,50,63,152],"query":[13],"within":[14],"audio":[16,30],"data.":[17],"Current":[18],"state-of-the-art":[19],"techniques":[20,40],"assume":[21],"zero":[22],"prior":[23],"knowledge":[24],"about":[25],"the":[26,29,42,72,86,101,105,162],"language":[27],"data,":[31],"and":[32,70,82,129],"thus":[33],"explore":[34],"dynamic":[35],"time":[36],"warping":[37],"(DTW)":[38],"based":[39,54],"for":[41,149,166],"QbE-STD":[43,75],"task.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,159],"use":[49],"variant":[51,137],"DTW":[53,60],"algorithm":[55],"referred":[56],"as":[58,111,119],"non-segmental":[59],"(NS-DTW),":[61],"with":[62,76],"computational":[64,163],"upper":[65,164],"bound":[66,165],"O":[68],"(mn)":[69],"analyze":[71],"performance":[73],"Gaussian":[77],"posteriorgrams":[78],"obtained":[79],"from":[80],"spectral":[81,116],"temporal":[83,102],"features":[84],"speech":[87,106],"signal.":[88],"results":[90],"show":[91,160],"that":[92,161],"frequency":[93],"domain":[94],"linear":[95,120,125],"prediction":[96,121,126],"cepstral":[97,122,127,131],"coefficients,":[98,123],"which":[99,144,174],"capture":[100],"dynamics":[103],"signal,":[107],"can":[108],"be":[109],"used":[110],"an":[112],"alternative":[113],"traditional":[115],"parameters":[117],"such":[118],"perceptual":[124],"coefficients":[128],"Mel-frequency":[130],"coefficients.":[132],"We":[133],"also":[134],"introduce":[135],"another":[136],"NS-DTW":[139,142],"called":[140],"fast":[141],"(FNS-DTW)":[143],"uses":[145],"reduced":[146],"feature":[147],"vectors":[148],"search.":[150],"With":[151],"reduction":[153],"factor":[154],"\u03b1":[156],"\u2208":[157],"\u2115,":[158],"FNS-DTW":[167],"O(mn/(\u03b1":[169],"<sup":[170],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[171],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[172],"))":[173],"faster":[176],"than":[177],"NS-DTW.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}