{"id":"https://openalex.org/W2902204479","doi":"https://doi.org/10.1109/icacci.2018.8554731","title":"Audio Mining: Unsupervised Spoken Term Detection over an Audio Database","display_name":"Audio Mining: Unsupervised Spoken Term Detection over an Audio Database","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2902204479","doi":"https://doi.org/10.1109/icacci.2018.8554731","mag":"2902204479"},"language":"en","primary_location":{"id":"doi:10.1109/icacci.2018.8554731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icacci.2018.8554731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","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/A5077838143","display_name":"Kishore Kumar R","orcid":null},"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":true,"raw_author_name":"Kishore Kumar R.","raw_affiliation_strings":["Department of Computer Science & Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sandipan Sarkar","orcid":null},"institutions":[{"id":"https://openalex.org/I1340206300","display_name":"Defence Research and Development Organisation","ror":"https://ror.org/05k37v296","country_code":"IN","type":"government","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210150591"]},{"id":"https://openalex.org/I4210125378","display_name":"Integrated Test Range","ror":"https://ror.org/02gvtkt16","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210125378","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sandipan Sarkar","raw_affiliation_strings":["Integrated Test Range, Defence Research and Development Organisation, India"],"affiliations":[{"raw_affiliation_string":"Integrated Test Range, Defence Research and Development Organisation, India","institution_ids":["https://openalex.org/I4210125378","https://openalex.org/I1340206300"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083000229","display_name":"Pradeep Rengaswamy","orcid":null},"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":"Pradeep Rengaswamy","raw_affiliation_strings":["Department of Computer Science & Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048234263","display_name":"K. Sreenivasa Rao","orcid":"https://orcid.org/0000-0002-2186-0419"},"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":"K. Sreenivasa Rao","raw_affiliation_strings":["Department of Computer Science & Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077838143"],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.142467,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"6","issue":null,"first_page":"514","last_page":"518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"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":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8337173461914062},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.748043417930603},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7430348992347717},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.6325900554656982},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6214203834533691},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.5748702883720398},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5437548756599426},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.46611908078193665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45335638523101807},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.42011559009552},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4146747589111328},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.386111319065094},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.3856920897960663},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37926051020622253},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3308321237564087},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3285709023475647},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.28756868839263916},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2695884704589844},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.249128520488739},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.19827887415885925},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.14305496215820312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8337173461914062},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.748043417930603},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7430348992347717},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.6325900554656982},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6214203834533691},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.5748702883720398},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5437548756599426},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.46611908078193665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45335638523101807},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.42011559009552},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4146747589111328},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.386111319065094},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.3856920897960663},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37926051020622253},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3308321237564087},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3285709023475647},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28756868839263916},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2695884704589844},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.249128520488739},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.19827887415885925},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.14305496215820312},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icacci.2018.8554731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icacci.2018.8554731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W114193738","https://openalex.org/W1490760466","https://openalex.org/W1606311031","https://openalex.org/W1963706776","https://openalex.org/W2049155070","https://openalex.org/W2055487029","https://openalex.org/W2057007397","https://openalex.org/W2069562432","https://openalex.org/W2098044214","https://openalex.org/W2114347655","https://openalex.org/W2114510609","https://openalex.org/W2126203737","https://openalex.org/W2128160875","https://openalex.org/W2137044559","https://openalex.org/W2139106564","https://openalex.org/W2145023731","https://openalex.org/W2171019095","https://openalex.org/W2401207139","https://openalex.org/W2963879374","https://openalex.org/W4205687621","https://openalex.org/W6604666349","https://openalex.org/W6662599187"],"related_works":["https://openalex.org/W2786391371","https://openalex.org/W2908089434","https://openalex.org/W1974745151","https://openalex.org/W2338585947","https://openalex.org/W1967853457","https://openalex.org/W1546240199","https://openalex.org/W3159882232","https://openalex.org/W1911859126","https://openalex.org/W46679383","https://openalex.org/W1969715806"],"abstract_inverted_index":{"Audio":[0],"mining,":[1],"also":[2],"called":[3],"audio":[4,51,74,87,136],"searching,":[5],"takes":[6],"a":[7],"spoken":[8,23,45,126,140],"query":[9,20,46,85,127,141],"and":[10,98,118],"locates":[11],"the":[12,40,44,50,63,93,100,104,125,134,139,147,153,163],"search":[13,21],"term":[14,24],"in":[15],"an":[16,28,107],"audio/speech":[17],"file.":[18],"Spoken":[19],"or":[22],"detection":[25],"(STD)":[26],"provides":[27],"efficient":[29],"means":[30],"for":[31],"content-based":[32],"retrieval":[33],"of":[34,43,73,84,133,146,162],"speech":[35,168],"files.":[36,75],"To":[37,96],"perform":[38],"STD,":[39],"posterior":[41,57,89],"features":[42,58,90],"as":[47,49],"well":[48,54],"files":[52,88,137],"are":[53,59,142],"utilized.":[55],"The":[56,144],"computed":[60,80],"by":[61],"training":[62],"Gaussian":[64],"mixture":[65],"model":[66],"(GMM)":[67],"with":[68,86,128],"mel-frequency":[69],"cepstral":[70],"coefficients":[71],"(MFCC)":[72],"A":[76],"distance":[77,105],"matrix":[78,106],"is":[79,112,150],"between":[81],"each":[82],"pair":[83],"to":[91],"examine":[92],"matched":[94,101,135],"portions.":[95],"identify":[97],"extract":[99],"portions":[102],"from":[103],"novel":[108],"pattern":[109],"identification":[110],"method":[111,149,165],"proposed":[113,130,148,164],"using":[114,152],"image":[115],"processing":[116,124],"techniques":[117],"dynamic":[119],"time":[120],"warping":[121],"(DTW).":[122],"By":[123],"our":[129],"method,":[131],"most":[132],"containing":[138],"retrieved.":[143],"performance":[145],"evaluated":[151],"standard":[154],"metric":[155],"like":[156],"average":[157],"precision":[158],"(AP).":[159],"For":[160],"experimentation":[161],"Hindi":[166],"news":[167],"data":[169],"was":[170],"used.":[171]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}