{"id":"https://openalex.org/W3010656005","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023023","title":"Query-by-Example Spoken Term Detection using Attentive Pooling Networks","display_name":"Query-by-Example Spoken Term Detection using Attentive Pooling Networks","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3010656005","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023023","mag":"3010656005"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5100342309","display_name":"Kun Zhang","orcid":"https://orcid.org/0000-0002-0738-9958"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Kun Zhang","raw_affiliation_strings":["Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Graduate School at Shenzhen, Tsinghua University, Shenzhen, China","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems Graduate School at Shenzhen, Tsinghua University Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Graduate School at Shenzhen, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems Graduate School at Shenzhen, Tsinghua University Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Graduate School at Shenzhen, Tsinghua University, Shenzhen, China","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems Graduate School at Shenzhen, Tsinghua University Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Graduate School at Shenzhen, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems Graduate School at Shenzhen, Tsinghua University Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405572","display_name":"Jia Jia","orcid":"https://orcid.org/0000-0002-7336-4003"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":["Department of Computer Science and Technology, Beijing National Research Centre for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","Beijing National Research Centre for Information Science and Technology (BNRist), Tsinghua University,Department of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Beijing National Research Centre for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing National Research Centre for Information Science and Technology (BNRist), Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR, China","The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Shatin, N.T., Hong Kong SAR,China"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Shatin, N.T., Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066803244","display_name":"Binheng Song","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Binheng Song","raw_affiliation_strings":["Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Graduate School at Shenzhen, Tsinghua University, Shenzhen, China","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems Graduate School at Shenzhen, Tsinghua University Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Graduate School at Shenzhen, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems Graduate School at Shenzhen, Tsinghua University Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100342309"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I889458895","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.6798345,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1267","last_page":"1272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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":0.8423182964324951},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.774146318435669},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6193959712982178},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5307514667510986},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5293313264846802},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5085688829421997},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5078848004341125},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4859563112258911},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4858355224132538},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.45910242199897766},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44789913296699524},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4264909327030182},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.30448058247566223},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1443357765674591},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11001566052436829}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8423182964324951},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.774146318435669},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6193959712982178},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5307514667510986},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5293313264846802},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5085688829421997},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5078848004341125},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4859563112258911},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4858355224132538},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.45910242199897766},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44789913296699524},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4264909327030182},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30448058247566223},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1443357765674591},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11001566052436829},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W49437105","https://openalex.org/W114193738","https://openalex.org/W1494198834","https://openalex.org/W1496120315","https://openalex.org/W1524333225","https://openalex.org/W2114347655","https://openalex.org/W2126203737","https://openalex.org/W2128160875","https://openalex.org/W2140277151","https://openalex.org/W2148986421","https://openalex.org/W2171019095","https://openalex.org/W2264105282","https://openalex.org/W2513125788","https://openalex.org/W2889270419","https://openalex.org/W2963879374","https://openalex.org/W6602023532","https://openalex.org/W6604666349","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W147410782","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W803346624"],"abstract_inverted_index":{"Query-by-example":[0],"spoken":[1,16,40],"term":[2],"detection":[3,65],"(QbE-STD)":[4],"is":[5,61,122],"attractive":[6],"because":[7],"its":[8],"a":[9,93,102,125,137],"key":[10],"technology":[11],"for":[12,33,86,116],"retrieving":[13],"and":[14,42,56,133,157],"browsing":[15],"content":[17],"without":[18],"transcribing":[19],"them":[20],"into":[21,48,76],"text.":[22],"Several":[23],"end-to-end":[24,117],"models":[25],"based":[26,67,107],"on":[27,68,108,153],"encoder":[28],"architecture":[29],"have":[30],"been":[31,74],"proposed":[32,166],"QbE-STD,":[34],"in":[35,136],"which":[36,90],"the":[37,69,77,129,146,154,162,170],"input":[38,131,141],"pair,":[39],"query":[41],"audio":[43,87,159],"segment,":[44],"are":[45],"first":[46],"projected":[47,130],"fixed-length":[49],"vector":[50,85],"representations":[51],"by":[52],"feature":[53,78,104],"extraction":[54,105],"module":[55,60,106],"then":[57],"similarity":[58,126],"measure":[59,127],"used":[62],"to":[63,123,169],"output":[64],"score":[66],"representations.":[70],"Attention":[71],"mechanism":[72],"has":[73],"applied":[75],"extractor;":[79],"however,":[80],"traditional":[81,171],"approach":[82,167],"calculates":[83],"attention":[84,95,110],"segment":[88],"only,":[89],"makes":[91],"it":[92],"one-way":[94],"mechanism.":[96],"In":[97],"this":[98],"paper,":[99],"we":[100],"present":[101],"novel":[103],"two-way":[109],"mechanism,":[111],"called":[112],"attentive":[113],"pooling":[114],"networks,":[115],"QbE-STD.":[118],"The":[119],"main":[120],"idea":[121],"learn":[124],"over":[128],"pair":[132],"extract":[134],"information":[135],"way":[138],"that":[139],"two":[140],"items":[142],"can":[143],"directly":[144],"influence":[145],"computation":[147],"of":[148,164],"each":[149],"other's":[150],"representation.":[151],"Evaluations":[152],"LibriSpeech":[155],"corpus":[156],"cross-linguistic":[158],"archive":[160],"confirm":[161],"effectiveness":[163],"our":[165],"compared":[168],"ones.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
