{"id":"https://openalex.org/W2399363370","doi":"https://doi.org/10.21437/interspeech.2014-394","title":"Intrinsic spectral analysis based on temporal context features for query-by-example spoken term detection","display_name":"Intrinsic spectral analysis based on temporal context features for query-by-example spoken term detection","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2399363370","doi":"https://doi.org/10.21437/interspeech.2014-394","mag":"2399363370"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-394","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/A5101863403","display_name":"Peng Yang","orcid":"https://orcid.org/0009-0005-3449-5843"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Peng Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113828649","display_name":"Cheung-Chi Leung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheung-Chi Leung","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066245750","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-9051-2111"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Agency for Science, Technology, and Research"],"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology, and Research","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Agency for Science, Technology, and Research"],"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology, and Research","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Agency for Science, Technology, and Research"],"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology, and Research","institution_ids":["https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101863403"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.0742,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.95625484,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1722","last_page":"1726"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9962999820709229,"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":0.9957000017166138,"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":0.8640190362930298},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8171707391738892},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6758682131767273},{"id":"https://openalex.org/keywords/coarticulation","display_name":"Coarticulation","score":0.5711832046508789},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5009498596191406},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.4966784119606018},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4816807210445404},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4747503101825714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4504653811454773},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.44156789779663086},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.21594130992889404},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.07122603058815002},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06989645957946777}],"concepts":[{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.8640190362930298},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8171707391738892},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6758682131767273},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.5711832046508789},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5009498596191406},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.4966784119606018},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4816807210445404},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4747503101825714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4504653811454773},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.44156789779663086},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.21594130992889404},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.07122603058815002},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06989645957946777},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2014-394","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.651.8151","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.651.8151","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.nwpu-aslp.org/lxie/papers/2014Interspeech-YangPeng.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6600000262260437,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W66167291","https://openalex.org/W1539935047","https://openalex.org/W1578200545","https://openalex.org/W2019368538","https://openalex.org/W2026704977","https://openalex.org/W2065136108","https://openalex.org/W2097703723","https://openalex.org/W2100580843","https://openalex.org/W2101094502","https://openalex.org/W2103372210","https://openalex.org/W2104290444","https://openalex.org/W2110589736","https://openalex.org/W2113605784","https://openalex.org/W2121947440","https://openalex.org/W2125534887","https://openalex.org/W2126203737","https://openalex.org/W2154085905","https://openalex.org/W2166343746","https://openalex.org/W2171019095","https://openalex.org/W2251863249","https://openalex.org/W2402963799","https://openalex.org/W2405703722"],"related_works":["https://openalex.org/W2022044030","https://openalex.org/W2990278625","https://openalex.org/W1993499045","https://openalex.org/W1604595447","https://openalex.org/W1984867078","https://openalex.org/W2150473580","https://openalex.org/W2786391371","https://openalex.org/W2338585947","https://openalex.org/W1974745151","https://openalex.org/W2944343977"],"abstract_inverted_index":{"We":[0],"investigate":[1],"the":[2,16,40,71,86,100,122,128,143,147],"use":[3,94],"of":[4,66],"intrinsic":[5,158],"spectral":[6,159],"analysis":[7],"(ISA)":[8],"for":[9,70],"query-by-example":[10],"spoken":[11,18,155],"term":[12,156],"detection":[13],"(QbE-STD).":[14],"In":[15],"task,":[17],"queries":[19],"and":[20,32,74,80],"test":[21,49],"utterances":[22,63],"in":[23,43,48,89,112,138],"an":[24,106],"audio":[25],"archive":[26],"are":[27],"converted":[28],"to":[29,38,59,85,93,98],"ISA":[30,55,101,129],"features,":[31,145],"dynamic":[33,163],"time":[34,164],"warping":[35,165],"is":[36,114,151],"applied":[37],"match":[39],"feature":[41],"sequence":[42],"each":[44],"query":[45],"with":[46,76],"those":[47],"utterances.":[50],"Motivated":[51],"by":[52],"manifold":[53],"learning,":[54],"has":[56],"been":[57],"pro-posed":[58],"recover":[60],"from":[61],"untranscribed":[62],"a":[64,116,133],"set":[65],"nonlin-ear":[67],"basis":[68],"functions":[69],"speech":[72,124],"manifold,":[73],"shown":[75],"improved":[77],"phonetic":[78],"separability":[79],"inherent":[81],"speaker":[82],"indepen-dence.":[83],"Due":[84],"coarticulation":[87],"phenomenon":[88],"speech,":[90],"we":[91],"propose":[92],"temporal":[95,148],"context":[96,149],"information":[97,150],"obtain":[99],"features.":[102],"Gaussian":[103,161],"posteriorgram,":[104,162],"as":[105],"efficient":[107],"acoustic":[108],"rep-resentation":[109],"usually":[110],"used":[111],"QbE-STD,":[113],"considered":[115],"baseline":[117,144],"feature.":[118],"Experimental":[119],"results":[120],"on":[121],"TIMIT":[123],"corpus":[125],"show":[126],"that":[127],"features":[130],"can":[131],"provide":[132],"relative":[134],"13.5":[135],"%":[136],"improvement":[137],"mean":[139],"average":[140],"precision":[141],"over":[142],"when":[146],"used.":[152],"Index":[153],"Terms:":[154],"detection,":[157],"analysis,":[160],"1.":[166]},"counts_by_year":[{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}