{"id":"https://openalex.org/W2889182547","doi":"https://doi.org/10.21437/interspeech.2018-1759","title":"On Convolutional LSTM Modeling for Joint Wake-Word Detection and Text Dependent Speaker Verification","display_name":"On Convolutional LSTM Modeling for Joint Wake-Word Detection and Text Dependent Speaker Verification","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889182547","doi":"https://doi.org/10.21437/interspeech.2018-1759","mag":"2889182547"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1759","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5082530526","display_name":"Rajath Kumar","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rajath Kumar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082829567","display_name":"Vaishnavi Yeruva","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vaishnavi Yeruva","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002536077","display_name":"Sriram Ganapathy","orcid":"https://orcid.org/0000-0002-5779-9066"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sriram Ganapathy","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082530526"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3538,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.85985413,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1121","last_page":"1125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9908000230789185,"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":0.9908000230789185,"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":0.8194255828857422},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.625006377696991},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6143639087677002},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.593974769115448},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5838865637779236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5796090960502625},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5043491125106812},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4239156246185303},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.22216671705245972},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11446079611778259},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06927379965782166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8194255828857422},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.625006377696991},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6143639087677002},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.593974769115448},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5838865637779236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5796090960502625},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5043491125106812},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4239156246185303},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.22216671705245972},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11446079611778259},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06927379965782166},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1759","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.iisc.ac.in:62919","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2955938200","https://openalex.org/W2748454020","https://openalex.org/W2998526951","https://openalex.org/W3119610945","https://openalex.org/W3107474891","https://openalex.org/W3042572036","https://openalex.org/W2746762848","https://openalex.org/W2288336858","https://openalex.org/W1988530429","https://openalex.org/W3205435834"],"abstract_inverted_index":{"The":[0,126],"task":[1,24],"of":[2,28,80,96,99,162,168,200],"personalized":[3,122],"keyword":[4,45,101,192],"detection":[5,34,95,134,193],"system":[6],"which":[7],"also":[8,179],"performs":[9],"text":[10,174],"dependent":[11,175],"speaker":[12],"verification":[13],"(TDSV)":[14],"has":[15],"received":[16],"substantial":[17],"interest":[18],"recently.":[19],"Conventional":[20],"approaches":[21],"to":[22],"this":[23,38],"involve":[25],"the":[26,29,53,85,91,97,100,106,109,117,138,159,166,183],"development":[27],"TDSV":[30,43,107,136],"and":[31,44,135,147],"wakeup":[32],"-word":[33],"systems":[35,194],"separately.":[36],"In":[37,150],"paper,":[39],"we":[40,88,156],"show":[41,89],"that":[42,90,158,182],"spotting":[46],"(KWS)":[47],"can":[48,112],"be":[49,113],"jointly":[50],"modeled":[51],"using":[52,116,137],"convolutional":[54,65],"long":[55],"short":[56],"term":[57],"memory":[58],"(CLSTM)":[59],"model":[60,92,111,185],"architecture,":[61],"where":[62],"an":[63],"initial":[64],"feature":[66],"map":[67],"is":[68],"further":[69],"processed":[70],"by":[71],"a":[72,77],"LSTM":[73],"recurrent":[74],"network.":[75],"Given":[76],"small":[78],"amount":[79],"training":[81,119],"data":[82],"for":[83,121,130],"developing":[84],"CLSTM":[86,118,184],"system,":[87],"provides":[93,186],"accurate":[94],"presence":[98],"in":[102],"spoken":[103],"utterance.":[104],"For":[105],"task,":[108],"MTL":[110,163],"well":[114,196],"regularized":[115],"examples":[120],"wake":[123,132],"up":[124,133],"task.":[125],"experiments":[127,152],"are":[128],"performed":[129],"KWS":[131],"combined":[139],"speech":[140],"recordings":[141],"from":[142],"Wall":[143],"Street":[144],"Journal":[145],"(WSJ)":[146],"LibriSpeech":[148],"corpus.":[149],"these":[151],"with":[153],"multiple":[154],"keywords,":[155],"illustrate":[157,181],"proposed":[160,170,191],"approach":[161],"significantly":[164],"improves":[165],"performance":[167],"previously":[169,190],"neural":[171],"network":[172],"based":[173],"SV":[176],"systems.":[177],"We":[178],"experimentally":[180],"significant":[187],"improvements":[188,199],"over":[189,202],"as":[195],"(average":[197],"relative":[198],"30%":[201],"previous":[203],"approaches).":[204]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}