{"id":"https://openalex.org/W2109173967","doi":"https://doi.org/10.1109/icassp.2011.5947642","title":"Integrating frame-based and segment-based dynamic time warping for unsupervised spoken term detection with spoken queries","display_name":"Integrating frame-based and segment-based dynamic time warping for unsupervised spoken term detection with spoken queries","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2109173967","doi":"https://doi.org/10.1109/icassp.2011.5947642","mag":"2109173967"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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/A5105193799","display_name":"Chun-an Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-an Chan","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","Graduate Inst. of Commun. Eng., Nat. Taiwan Univ., Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Graduate Inst. of Commun. Eng., Nat. Taiwan Univ., Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044010123","display_name":"Lin-shan Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Lin-shan Lee","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","Graduate Inst. of Commun. Eng., Nat. Taiwan Univ., Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Graduate Inst. of Commun. Eng., Nat. Taiwan Univ., Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":1.3902,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.82230306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5652","last_page":"5655"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","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/T12205","display_name":"Time Series Analysis and Forecasting","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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.9853000044822693,"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/dynamic-time-warping","display_name":"Dynamic time warping","score":0.9636093378067017},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.838536262512207},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6977189183235168},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6310759782791138},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5991336107254028},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5255217552185059},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5120800137519836},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4490271508693695},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.44702059030532837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4468485116958618},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4231933355331421},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32285866141319275},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14035102725028992},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10096704959869385}],"concepts":[{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.9636093378067017},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.838536262512207},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6977189183235168},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6310759782791138},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5991336107254028},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5255217552185059},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5120800137519836},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4490271508693695},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.44702059030532837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4468485116958618},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4231933355331421},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32285866141319275},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14035102725028992},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10096704959869385},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1815792","https://openalex.org/W27865004","https://openalex.org/W49437105","https://openalex.org/W114193738","https://openalex.org/W1606311031","https://openalex.org/W2028282769","https://openalex.org/W2126203737","https://openalex.org/W2171019095","https://openalex.org/W6602023532","https://openalex.org/W6604666349"],"related_works":["https://openalex.org/W2341338763","https://openalex.org/W2950183183","https://openalex.org/W2030799363","https://openalex.org/W2032415964","https://openalex.org/W2288425735","https://openalex.org/W2349923317","https://openalex.org/W2894081631","https://openalex.org/W2986063033","https://openalex.org/W1544128162","https://openalex.org/W91730491"],"abstract_inverted_index":{"ABSTRACT":[0],"Rapidly":[1],"increasing":[2],"quantities":[3],"of":[4,27,36,74,90,93,153],"multimedia":[5],"and":[6,13,30,131],"spoken":[7,22,128],"con":[8,18],"tent":[9],"today":[10],"demand":[11],"fast":[12],"accurate":[14],"retrieval":[15],"approaches":[16],"for":[17,135],"venient":[19],"browsing.":[20],"The":[21,99,116],"documents":[23],"with":[24,57],"wide":[25],"variety":[26],"different":[28],"acoustic":[29,151],"linguistic":[31],"conditions":[32],"make":[33],"supervised":[34],"training":[35],"well-matched":[37],"acoustic/language":[38,54],"models":[39,55],"very":[40],"difficult.":[41],"Unsuper":[42],"vised":[43],"methods":[44],"using":[45],"frame-based":[46,133,170],"dynamic":[47],"time":[48],"warping":[49],"(DTW)":[50],"re":[51],"quire":[52],"no":[53],"but":[56],"high":[58],"computation":[59,69,165],"load.":[60],"Therefore,":[61],"segment-based":[62,85],"DTW":[63,86,118,134],"was":[64],"proposed":[65],"to":[66,95,125,149,169],"relieve":[67],"the":[68,72,84,122,132,139,143,154],"load":[70,166],"at":[71,162],"cost":[73],"degraded":[75],"detection":[76,97,160],"performance.":[77,98],"In":[78],"this":[79],"pa":[80],"per,":[81],"we":[82],"refine":[83],"by":[87,105],"allowing":[88],"deletion":[89],"end":[91],"segments":[92],"query":[94],"improve":[96],"search":[100],"space":[101],"is":[102,119,147],"also":[103,110],"reduced":[104],"segment":[106],"similarity":[107],"constraints.":[108],"We":[109,156],"pro":[111],"posed":[112],"a":[113],"two-pass":[114],"framework.":[115],"segment-baed":[117],"performed":[120],"in":[121,138],"first":[123],"pass":[124],"locate":[126],"hypothesized":[127],"term":[129],"region":[130],"precise":[136],"rescoring":[137],"second":[140],"pass.":[141],"Then":[142],"pseudo":[144],"relevance":[145],"feedback":[146],"used":[148],"expand":[150],"variations":[152],"query.":[155],"obtain":[157],"significantly":[158,163],"higher":[159],"performance":[161],"lower":[164],"as":[167],"compared":[168],"DTW.":[171]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}