{"id":"https://openalex.org/W1976959370","doi":"https://doi.org/10.1109/icassp.2014.6854984","title":"Unsupervised query-by-example spoken term detection using segment-based Bag of Acoustic Words","display_name":"Unsupervised query-by-example spoken term detection using segment-based Bag of Acoustic Words","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1976959370","doi":"https://doi.org/10.1109/icassp.2014.6854984","mag":"1976959370"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854984","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5105776451","display_name":"Basil George","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"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Basil George","raw_affiliation_strings":["Speech and Vision Lab, International Institute of Information Technology, Hyderabad, India","Speech & Vision Lab., Int. Inst. of Inf. Technol., Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Vision Lab, International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]},{"raw_affiliation_string":"Speech & Vision Lab., Int. Inst. of Inf. Technol., Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079329589","display_name":"B. Yegnanarayana","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"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"B. Yegnanarayana","raw_affiliation_strings":["Speech and Vision Lab, International Institute of Information Technology, Hyderabad, India","Speech & Vision Lab., Int. Inst. of Inf. Technol., Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Vision Lab, International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]},{"raw_affiliation_string":"Speech & Vision Lab., Int. Inst. of Inf. Technol., Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7133","last_page":"7137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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":0.9965999722480774,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9954000115394592,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9925000071525574,"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":0.8727942705154419},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.8723866939544678},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.8454908728599548},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8024572730064392},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6888757348060608},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5655032992362976},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4934781789779663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.465084969997406},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4599240720272064},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.44452473521232605},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.43211066722869873},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3406679034233093},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32671058177948}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8727942705154419},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.8723866939544678},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8454908728599548},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8024572730064392},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6888757348060608},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5655032992362976},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4934781789779663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.465084969997406},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4599240720272064},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.44452473521232605},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.43211066722869873},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3406679034233093},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32671058177948},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/icassp.2014.6854984","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":18,"referenced_works":["https://openalex.org/W1815792","https://openalex.org/W40730796","https://openalex.org/W49437105","https://openalex.org/W114193738","https://openalex.org/W2015688877","https://openalex.org/W2030694415","https://openalex.org/W2107076535","https://openalex.org/W2110625382","https://openalex.org/W2126203737","https://openalex.org/W2131846894","https://openalex.org/W2158102958","https://openalex.org/W2171019095","https://openalex.org/W2186490579","https://openalex.org/W2395865585","https://openalex.org/W2403207842","https://openalex.org/W2407964052","https://openalex.org/W6602023532","https://openalex.org/W6604666349"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W2088615611","https://openalex.org/W2117995638"],"abstract_inverted_index":{"In":[0],"this":[1,45,99],"work,":[2],"we":[3],"present":[4],"an":[5,88],"unsupervised":[6],"framework":[7,27,100],"to":[8,71],"address":[9,108],"the":[10,32,48,58,73,77,93,109,113,117,134,138],"problem":[11],"of":[12,23,34,57,111,116,119],"spotting":[13],"spoken":[14,128],"terms":[15],"in":[16,40,51,87],"large":[17,105],"speech":[18,52,82,120],"databases.":[19,106],"The":[20,81],"segment-based":[21],"Bag":[22,33],"Acoustic":[24],"Words":[25,35],"(BoAW)":[26],"proposed":[28,135],"is":[29,69,84],"inspired":[30],"from":[31],"(BoW)":[36],"approach":[37],"widely":[38],"used":[39,70],"text":[41],"retrieval":[42,94],"systems.":[43],"Since":[44],"model":[46],"ignores":[47],"sequence":[49,79],"information":[50],"samples":[53],"for":[54,103,121],"efficient":[55],"indexing":[56],"database,":[59],"a":[60],"Dynamic":[61],"Time":[62],"Warping":[63],"(DTW)":[64],"based":[65],"temporal":[66],"matching":[67],"technique":[68],"re-rank":[72],"results":[74],"and":[75],"restore":[76],"time":[78],"information.":[80],"data":[83],"stored":[85],"efficiently":[86],"inverted":[89],"index":[90],"which":[91],"makes":[92],"very":[95],"fast,":[96],"thus":[97],"making":[98],"particularly":[101],"useful":[102],"searching":[104],"We":[107],"issue":[110],"choosing":[112],"appropriate":[114],"size":[115],"segment":[118],"reliable":[122],"indexing.":[123],"Comparison":[124],"with":[125],"other":[126],"query-by-example":[127],"term":[129],"detection":[130],"systems":[131],"shows":[132],"that":[133],"system":[136],"outperforms":[137],"rest.":[139]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}