{"id":"https://openalex.org/W4220771609","doi":"https://doi.org/10.1109/icce53296.2022.9730179","title":"A Two-Stage LSTM Based Approach for Voice Activity Detection with Sound Event Classification","display_name":"A Two-Stage LSTM Based Approach for Voice Activity Detection with Sound Event Classification","publication_year":2022,"publication_date":"2022-01-07","ids":{"openalex":"https://openalex.org/W4220771609","doi":"https://doi.org/10.1109/icce53296.2022.9730179"},"language":"en","primary_location":{"id":"doi:10.1109/icce53296.2022.9730179","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce53296.2022.9730179","pdf_url":null,"source":{"id":"https://openalex.org/S4363608007","display_name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","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/A5016536475","display_name":"Yarong Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Yarong Feng","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051296523","display_name":"Zongyi Joe Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zongyi Joe Liu","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078449424","display_name":"Yuan Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yuan Ling","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010439249","display_name":"Bruce Ferry","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bruce Ferry","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016536475"],"corresponding_institution_ids":["https://openalex.org/I4210089985"],"apc_list":null,"apc_paid":null,"fwci":0.3677,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.46382306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"7","issue":null,"first_page":"1","last_page":"6"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9955000281333923,"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":0.7168272137641907},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6512086391448975},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.640835165977478},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5795435905456543},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5731920003890991},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5688827037811279},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5497034192085266},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5260351300239563},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.476817786693573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7168272137641907},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6512086391448975},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.640835165977478},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5795435905456543},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5731920003890991},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5688827037811279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5497034192085266},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5260351300239563},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.476817786693573},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/icce53296.2022.9730179","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce53296.2022.9730179","pdf_url":null,"source":{"id":"https://openalex.org/S4363608007","display_name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Consumer Electronics (ICCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2408239454","https://openalex.org/W2593116425","https://openalex.org/W2810934215","https://openalex.org/W3094550259","https://openalex.org/W3116725331","https://openalex.org/W4287826698","https://openalex.org/W6774581290","https://openalex.org/W6788667078"],"related_works":["https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W1999699871","https://openalex.org/W2342291550","https://openalex.org/W2971899271","https://openalex.org/W2021633306","https://openalex.org/W17944005","https://openalex.org/W2006801911","https://openalex.org/W1972167985","https://openalex.org/W1968350661"],"abstract_inverted_index":{"We":[0],"introduce":[1,45],"a":[2],"two-stage":[3],"approach":[4,16],"using":[5,34],"LSTM":[6],"for":[7,48,71,77,84],"voice":[8],"activity":[9],"detection":[10],"with":[11],"sound":[12],"event":[13],"classification.":[14],"This":[15],"proves":[17],"to":[18],"be":[19],"effective":[20],"when":[21],"training":[22],"data":[23,36],"is":[24],"limited.":[25],"Moreover,":[26],"it":[27],"achieves":[28,64],"better":[29],"performance":[30],"than":[31],"pre-trained":[32],"model":[33],"large-scale":[35],"set":[37],"(AudioSet).":[38],"Apart":[39],"from":[40],"clip-level":[41],"accuracy,":[42,67],"we":[43],"also":[44],"two":[46],"metrics":[47],"evaluating":[49],"overall":[50],"audio":[51],"segmentation":[52],"accuracy:":[53],"mean":[54,56,69,75,81],"<tex>$\\mathbf{IoU}$</tex>),and":[55],"front":[57,82],"miss.":[58],"On":[59],"test":[60],"set,":[61],"our":[62],"method":[63],"98":[65],"&#x0025;":[66],"0.95":[68],"<tex>$\\mathbf{IoU}$</tex>":[70,76],"speech":[72,86],"and":[73,79,87],"0.99":[74],"music,":[78],"0.03":[80],"miss":[83],"both":[85],"music.":[88]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}