{"id":"https://openalex.org/W3011882980","doi":"https://doi.org/10.1109/ialp48816.2019.9037714","title":"An End-to-End Model Based on TDNN-BiGRU for Keyword Spotting","display_name":"An End-to-End Model Based on TDNN-BiGRU for Keyword Spotting","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011882980","doi":"https://doi.org/10.1109/ialp48816.2019.9037714","mag":"3011882980"},"language":"en","primary_location":{"id":"doi:10.1109/ialp48816.2019.9037714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp48816.2019.9037714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Asian Language Processing (IALP)","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/A5036170008","display_name":"Shuzhou Chai","orcid":null},"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":"Shuzhou Chai","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041672656","display_name":"Zhenye Yang","orcid":null},"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":"Zhenye Yang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031671759","display_name":"Changsheng Lv","orcid":null},"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":"Changsheng Lv","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"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":"Wei-Qiang Zhang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2019","issue":null,"first_page":"402","last_page":"406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9995999932289124,"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":0.9993000030517578,"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/softmax-function","display_name":"Softmax function","score":0.8920447826385498},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7706942558288574},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6246963143348694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5764164924621582},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5602192878723145},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5052292943000793},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.5008583068847656},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.4937964379787445},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.4898469150066376},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.43907618522644043}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8920447826385498},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706942558288574},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6246963143348694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5764164924621582},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5602192878723145},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5052292943000793},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.5008583068847656},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.4937964379787445},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.4898469150066376},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.43907618522644043}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ialp48816.2019.9037714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp48816.2019.9037714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"},{"id":"mag:3043950242","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002273086924784","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W114193738","https://openalex.org/W1522301498","https://openalex.org/W1734538896","https://openalex.org/W1995945045","https://openalex.org/W1999121090","https://openalex.org/W2029949252","https://openalex.org/W2034940213","https://openalex.org/W2056986588","https://openalex.org/W2156431836","https://openalex.org/W2296516251","https://openalex.org/W2407023693","https://openalex.org/W2558258029","https://openalex.org/W2587529061","https://openalex.org/W2953219395","https://openalex.org/W2962959915","https://openalex.org/W2964121744","https://openalex.org/W2964187693","https://openalex.org/W3098773154","https://openalex.org/W4253020087","https://openalex.org/W4294621971","https://openalex.org/W6604666349","https://openalex.org/W6631190155","https://openalex.org/W6649874456","https://openalex.org/W6664384591","https://openalex.org/W6697811694","https://openalex.org/W6714171909","https://openalex.org/W6729959887","https://openalex.org/W6844803729"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W3119978414","https://openalex.org/W4286904253","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"proposed":[4],"a":[5,53,93,100],"neural":[6],"network":[7],"architecture":[8],"based":[9],"on":[10],"Time-Delay":[11],"Neural":[12],"Network":[13],"(TDNN)Bidirectional":[14],"Gated":[15],"Recurrent":[16],"Unit":[17],"(BiGRU)":[18],"for":[19],"small-footprint":[20],"keyWord":[21],"spotting.":[22],"Our":[23,89],"model":[24,90],"consists":[25],"of":[26,46,55,83,97],"three":[27],"parts:":[28],"TDNN,":[29],"BiGRU":[30,40],"and":[31,39,72,80,85],"Attention":[32],"Mechanism.":[33],"TDNN":[34,84],"models":[35],"the":[36,42,47,65,77],"time":[37],"information":[38],"extracts":[41],"hidden":[43,59],"layer":[44,60],"features":[45],"audio.":[48],"The":[49,62],"attention":[50,87],"mechanism":[51],"generates":[52,64],"vector":[54,69],"fixed":[56],"length":[57],"with":[58],"features.":[61],"system":[63],"final":[66],"score":[67],"through":[68],"linear":[70],"transformation":[71],"softmax":[73],"function.":[74],"We":[75],"explored":[76],"step":[78],"size":[79,82],"unit":[81],"two":[86],"mechanisms.":[88],"has":[91],"achieved":[92],"true":[94],"positive":[95,103],"rate":[96],"99.63%":[98],"at":[99],"5%":[101],"false":[102],"rate.":[104]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}