{"id":"https://openalex.org/W3160747466","doi":"https://doi.org/10.1109/icassp39728.2021.9414470","title":"MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection","display_name":"MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160747466","doi":"https://doi.org/10.1109/icassp39728.2021.9414470","mag":"3160747466"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5011196247","display_name":"Fei Jia","orcid":"https://orcid.org/0000-0001-5212-6551"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Jia","raw_affiliation_strings":["NVIDIA, Santa Clara, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027823948","display_name":"Somshubra Majumdar","orcid":"https://orcid.org/0000-0001-5635-4893"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Somshubra Majumdar","raw_affiliation_strings":["NVIDIA, Santa Clara, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA, Santa Clara, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6818","last_page":"6822"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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":0.9991999864578247,"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":0.9987999796867371,"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/normalization","display_name":"Normalization (sociology)","score":0.7956854104995728},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.728140652179718},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7195227742195129},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6973448991775513},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.678635835647583},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6083675026893616},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5806820392608643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4904331862926483},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.48011326789855957},{"id":"https://openalex.org/keywords/separable-space","display_name":"Separable space","score":0.4744721055030823},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.42892494797706604},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41844555735588074},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41752520203590393},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22938784956932068},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18135932087898254},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12872037291526794},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0992760956287384}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7956854104995728},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.728140652179718},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7195227742195129},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6973448991775513},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.678635835647583},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6083675026893616},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5806820392608643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4904331862926483},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.48011326789855957},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.4744721055030823},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.42892494797706604},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41844555735588074},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41752520203590393},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22938784956932068},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18135932087898254},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12872037291526794},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0992760956287384},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":41,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1522301498","https://openalex.org/W1563939609","https://openalex.org/W1999454387","https://openalex.org/W2033875152","https://openalex.org/W2059203007","https://openalex.org/W2109788549","https://openalex.org/W2115717467","https://openalex.org/W2129120544","https://openalex.org/W2181253919","https://openalex.org/W2194775991","https://openalex.org/W2513345070","https://openalex.org/W2531409750","https://openalex.org/W2746314669","https://openalex.org/W2767895109","https://openalex.org/W2781384251","https://openalex.org/W2792351646","https://openalex.org/W2797583228","https://openalex.org/W2885307078","https://openalex.org/W2892300106","https://openalex.org/W2936299888","https://openalex.org/W2936774411","https://openalex.org/W2953333557","https://openalex.org/W2963855133","https://openalex.org/W2964121744","https://openalex.org/W2973215447","https://openalex.org/W2974231335","https://openalex.org/W2981728176","https://openalex.org/W3015537910","https://openalex.org/W3017216675","https://openalex.org/W3024085360","https://openalex.org/W3097018422","https://openalex.org/W3097148135","https://openalex.org/W4297818305","https://openalex.org/W6604254268","https://openalex.org/W6631190155","https://openalex.org/W6743428213","https://openalex.org/W6747270024","https://openalex.org/W6750665317","https://openalex.org/W6765069029","https://openalex.org/W6767671539"],"related_works":["https://openalex.org/W3082178636","https://openalex.org/W1521968289","https://openalex.org/W4297807321","https://openalex.org/W3158431807","https://openalex.org/W2530952058","https://openalex.org/W2582836483","https://openalex.org/W4299366318","https://openalex.org/W4297580547","https://openalex.org/W2951583185","https://openalex.org/W4308155352"],"abstract_inverted_index":{"We":[0,51],"present":[1],"MarbleNet,":[2],"an":[3],"end-to-end":[4],"neural":[5],"network":[6,17],"for":[7],"Voice":[8],"Activity":[9],"Detection":[10],"(VAD).":[11],"MarbleNet":[12,38,72],"is":[13,39],"a":[14,34],"deep":[15],"residual":[16],"composed":[18],"from":[19],"blocks":[20],"of":[21,63,71],"1D":[22],"time-channel":[23],"separable":[24],"convolution,":[25],"batch-normalization,":[26],"ReLU":[27],"and":[28,61],"dropout":[29],"layers.":[30],"When":[31],"compared":[32],"to":[33,41,67],"state-of-the-art":[35],"VAD":[36,75],"model,":[37],"able":[40],"achieve":[42],"similar":[43],"performance":[44],"with":[45],"roughly":[46],"1/10-th":[47],"the":[48,69],"parameter":[49],"cost.":[50],"further":[52],"conduct":[53],"extensive":[54],"ablation":[55],"studies":[56],"on":[57],"different":[58],"training":[59],"methods":[60],"choices":[62],"parameters":[64],"in":[65,73],"order":[66],"study":[68],"robustness":[70],"real-world":[74],"tasks.":[76]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}