{"id":"https://openalex.org/W2908089434","doi":"https://doi.org/10.1109/icapr.2017.8593033","title":"Two Stage Zero-resource Approaches for QbE-STD","display_name":"Two Stage Zero-resource Approaches for QbE-STD","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2908089434","doi":"https://doi.org/10.1109/icapr.2017.8593033","mag":"2908089434"},"language":"en","primary_location":{"id":"doi:10.1109/icapr.2017.8593033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icapr.2017.8593033","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":"conference-paper","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/A5048910634","display_name":"Maulik C. Madhavi","orcid":"https://orcid.org/0000-0001-8743-6437"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Maulik C. Madhavi","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), India","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23131058,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9980000257492065,"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":0.9037256240844727},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8852584362030029},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7904098033905029},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.6754247546195984},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6621642112731934},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5654813051223755},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.49294209480285645},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.43326640129089355},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4228094816207886},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.42065003514289856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3288741409778595},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.27545297145843506},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.15273991227149963},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11145484447479248},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.08046641945838928},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07881763577461243}],"concepts":[{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.9037256240844727},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8852584362030029},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7904098033905029},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.6754247546195984},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6621642112731934},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5654813051223755},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.49294209480285645},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.43326640129089355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4228094816207886},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.42065003514289856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3288741409778595},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27545297145843506},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.15273991227149963},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11145484447479248},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.08046641945838928},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07881763577461243},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icapr.2017.8593033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icapr.2017.8593033","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W57926798","https://openalex.org/W103757200","https://openalex.org/W170732776","https://openalex.org/W1461662404","https://openalex.org/W1550888325","https://openalex.org/W1885329076","https://openalex.org/W1963706776","https://openalex.org/W1966264494","https://openalex.org/W1976959370","https://openalex.org/W1984076147","https://openalex.org/W1998766338","https://openalex.org/W2009341345","https://openalex.org/W2090777335","https://openalex.org/W2090861223","https://openalex.org/W2100580843","https://openalex.org/W2126203737","https://openalex.org/W2135934764","https://openalex.org/W2137044559","https://openalex.org/W2148154194","https://openalex.org/W2154093685","https://openalex.org/W2164365067","https://openalex.org/W2168080440","https://openalex.org/W2171019095","https://openalex.org/W2289281333","https://openalex.org/W2401857988","https://openalex.org/W2407080277","https://openalex.org/W2407151108","https://openalex.org/W2510719762","https://openalex.org/W2598392802","https://openalex.org/W6628602744","https://openalex.org/W6713034805"],"related_works":["https://openalex.org/W2347413598","https://openalex.org/W2335896301","https://openalex.org/W2330863229","https://openalex.org/W2012393389","https://openalex.org/W2333240621","https://openalex.org/W2137764249","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W3006618853","https://openalex.org/W2154472250"],"abstract_inverted_index":{"In":[0,49,79],"this":[1,50],"paper,":[2,51],"we":[3,52,62,83],"explore":[4],"the":[5,8,25,29,39,44,74,80,105,120,144,149],"information":[6,42],"in":[7,31,111,137,151],"acoustic":[9,86],"representation":[10],"for":[11,57],"Query-by-Example":[12],"Spoken":[13],"Term":[14,139],"Detection":[15],"(QbE-STD)":[16],"task.":[17],"Several":[18],"approaches":[19],"have":[20],"been":[21],"employed":[22],"to":[23,37,72,123,155],"detect":[24,38,73],"spoken":[26],"instance":[27],"of":[28,46,100,108,116,147],"query":[30],"audio":[32,77],"databases.":[33,78],"Zero-resource":[34],"approach":[35],"attempts":[36],"acoustically":[40],"similar":[41],"without":[43],"use":[45],"phone":[47],"recognizer.":[48],"present":[53],"two-stage":[54],"frame-level":[55],"matching":[56],"QbE-STD.":[58],"At":[59],"first":[60],"stage,":[61,82],"used":[63],"Gaussian":[64,163],"posteriorgram":[65,125],"and":[66,104],"subsequence":[67],"dynamic":[68],"time":[69],"warping":[70],"(subDTW)":[71],"segments":[75],"within":[76],"second":[81],"exploited":[84],"several":[85],"features":[87],"along":[88],"with":[89,143],"Dynamic":[90],"Time":[91],"Warping":[92],"(DTW)":[93],"detection":[94,109],"cues":[95],"such":[96],"as":[97,153],"cosine":[98],"similarity":[99],"term":[101],"frequency":[102],"vectors":[103],"valley":[106],"depth":[107],"obtained":[110,131],"subDTW.":[112],"The":[113],"score-level":[114,145],"fusion":[115,146],"search":[117],"system":[118],"gave":[119],"performance":[121],"comparable":[122],"phonetic":[124],"on":[126,157],"SWS":[127],"2013":[128],"database.":[129],"We":[130],"0.045":[132],"(i.e.,":[133],"4.5":[134],"%)":[135],"improvement":[136],"Maximum":[138],"Weighted":[140],"Value":[141],"(MTWV)":[142],"all":[148],"evidence":[150],"MTWV":[152],"compared":[154],"subDTW":[156],"Mel":[158],"Frequency":[159],"Cepstral":[160],"Coefficients":[161],"(MFCC)":[162],"posteriorgram.":[164]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}