{"id":"https://openalex.org/W2246941141","doi":"https://doi.org/10.1109/fskd.2015.7382134","title":"Query-by-example spoken term detection using bottleneck feature and Hidden Markov model","display_name":"Query-by-example spoken term detection using bottleneck feature and Hidden Markov model","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2246941141","doi":"https://doi.org/10.1109/fskd.2015.7382134","mag":"2246941141"},"language":"en","primary_location":{"id":"doi:10.1109/fskd.2015.7382134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2015.7382134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)","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/A5101501086","display_name":"Xue Liu","orcid":"https://orcid.org/0000-0002-7854-7845"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Liu","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language, Information Processing University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language, Information Processing University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Guo","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language, Information Processing University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language, Information Processing University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052232715","display_name":"Niansong Wang","orcid":"https://orcid.org/0000-0002-5265-5792"},"institutions":[{"id":"https://openalex.org/I4210139944","display_name":"Institute of Forensic Science","ror":"https://ror.org/04ry60e05","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210089256","https://openalex.org/I4210127390","https://openalex.org/I4210139944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Niansong Wang","raw_affiliation_strings":["Anhui Public Security Department, Institute of Forensic Science, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Public Security Department, Institute of Forensic Science, Hefei, China","institution_ids":["https://openalex.org/I4210139944"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1319","last_page":"1323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.8582666516304016},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8481258153915405},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.8015189170837402},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7229510545730591},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6846219897270203},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6482911109924316},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.5369266271591187},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5182359218597412},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5140689611434937},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4393007457256317},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3520251512527466},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.13508254289627075},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.102876216173172},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.06309905648231506},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06209081411361694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8582666516304016},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8481258153915405},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.8015189170837402},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7229510545730591},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6846219897270203},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6482911109924316},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.5369266271591187},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5182359218597412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5140689611434937},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4393007457256317},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3520251512527466},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.13508254289627075},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.102876216173172},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.06309905648231506},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06209081411361694},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fskd.2015.7382134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2015.7382134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W217970951","https://openalex.org/W943204654","https://openalex.org/W1520663776","https://openalex.org/W1815165135","https://openalex.org/W1984806059","https://openalex.org/W2012897754","https://openalex.org/W2028547769","https://openalex.org/W2044893557","https://openalex.org/W2062164080","https://openalex.org/W2066561607","https://openalex.org/W2074671152","https://openalex.org/W2090861223","https://openalex.org/W2100495367","https://openalex.org/W2106051978","https://openalex.org/W2108819501","https://openalex.org/W2110589736","https://openalex.org/W2122797512","https://openalex.org/W2126203737","https://openalex.org/W2145215282","https://openalex.org/W2147768505","https://openalex.org/W2153426278","https://openalex.org/W2160815625","https://openalex.org/W2171506966","https://openalex.org/W2184045248","https://openalex.org/W2394932179","https://openalex.org/W2396630453","https://openalex.org/W2402963799","https://openalex.org/W6608710415","https://openalex.org/W6624852173","https://openalex.org/W6631271284","https://openalex.org/W6638352220"],"related_works":["https://openalex.org/W2419138286","https://openalex.org/W2507549656","https://openalex.org/W2050318184","https://openalex.org/W101156158","https://openalex.org/W2182848507","https://openalex.org/W2387825067","https://openalex.org/W2506414444","https://openalex.org/W2786391371","https://openalex.org/W1974745151","https://openalex.org/W2338585947"],"abstract_inverted_index":{"Query":[0],"by":[1],"example":[2],"spoken":[3,14,17],"term":[4],"detection":[5],"(QbE-STD)":[6],"is":[7,31,54],"an":[8,93],"effective":[9],"search":[10],"mechanism":[11],"to":[12,43,56,71,91],"find":[13],"queries":[15],"in":[16,35,98],"audio,":[18],"especially":[19],"for":[20],"the":[21,32,45,49,58,64,73,82,85,105],"source":[22],"limited":[23],"language.":[24],"The":[25,77],"dynamic":[26],"time":[27],"warping":[28],"(DTW)":[29],"algorithm":[30,34],"state-of-art":[33],"this":[36],"area.":[37],"This":[38],"paper":[39],"presents":[40],"some":[41],"methods":[42],"improve":[44],"QbE-STD":[46],"performance.":[47],"First,":[48],"hidden":[50],"Markov":[51],"model":[52,57],"(HMM)":[53],"adopted":[55],"keyword":[59],"templates.":[60],"Second,":[61],"we":[62],"apply":[63],"deep":[65],"neural":[66],"network":[67],"(DNN)":[68],"bottleneck":[69],"feature":[70],"replace":[72],"traditional":[74],"acoustic":[75],"feature.":[76],"experimental":[78],"results":[79],"have":[80],"demonstrated":[81],"effectiveness":[83],"of":[84],"proposed":[86],"methods.":[87],"We":[88],"are":[89],"able":[90],"achieve":[92],"about":[94],"6%":[95],"absolute":[96],"improvement":[97],"F1":[99],"on":[100],"a":[101],"Tibetan":[102],"corpus":[103],"over":[104],"previous":[106],"best":[107],"baseline.":[108]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
