{"id":"https://openalex.org/W4390493598","doi":"https://doi.org/10.1109/cisp-bmei60920.2023.10373253","title":"SAPVAD: An Efficient Voice Activity Detection Model Based on Spectral Attention and Parallel Structure","display_name":"SAPVAD: An Efficient Voice Activity Detection Model Based on Spectral Attention and Parallel Structure","publication_year":2023,"publication_date":"2023-10-28","ids":{"openalex":"https://openalex.org/W4390493598","doi":"https://doi.org/10.1109/cisp-bmei60920.2023.10373253"},"language":"en","primary_location":{"id":"doi:10.1109/cisp-bmei60920.2023.10373253","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cisp-bmei60920.2023.10373253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 16th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","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/A5100434198","display_name":"Jiaqi Chen","orcid":"https://orcid.org/0000-0002-6368-6164"},"institutions":[{"id":"https://openalex.org/I1793135","display_name":"Yanbian University","ror":"https://ror.org/039xnh269","country_code":"CN","type":"education","lineage":["https://openalex.org/I1793135"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaqi Chen","raw_affiliation_strings":["Yanbian University,Integration College,Yanji,China","Integration College, Yanbian University, Yanji, China"],"affiliations":[{"raw_affiliation_string":"Yanbian University,Integration College,Yanji,China","institution_ids":["https://openalex.org/I1793135"]},{"raw_affiliation_string":"Integration College, Yanbian University, Yanji, China","institution_ids":["https://openalex.org/I1793135"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089390321","display_name":"Xiaofeng Jin","orcid":"https://orcid.org/0000-0003-1892-3439"},"institutions":[{"id":"https://openalex.org/I1793135","display_name":"Yanbian University","ror":"https://ror.org/039xnh269","country_code":"CN","type":"education","lineage":["https://openalex.org/I1793135"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Jin","raw_affiliation_strings":["Yanbian University,College of Engineering,Yanji,China,133002"],"affiliations":[{"raw_affiliation_string":"Yanbian University,College of Engineering,Yanji,China,133002","institution_ids":["https://openalex.org/I1793135"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100783079","display_name":"Guirong Wang","orcid":"https://orcid.org/0000-0002-2353-6241"},"institutions":[{"id":"https://openalex.org/I1793135","display_name":"Yanbian University","ror":"https://ror.org/039xnh269","country_code":"CN","type":"education","lineage":["https://openalex.org/I1793135"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guirong Wang","raw_affiliation_strings":["Yanbian University,College of Engineering,Yanji,China,133002"],"affiliations":[{"raw_affiliation_string":"Yanbian University,College of Engineering,Yanji,China,133002","institution_ids":["https://openalex.org/I1793135"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100582065","display_name":"Mingdong Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I1793135","display_name":"Yanbian University","ror":"https://ror.org/039xnh269","country_code":"CN","type":"education","lineage":["https://openalex.org/I1793135"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingdong Yu","raw_affiliation_strings":["Yanbian University,College of Engineering,Yanji,China,133002"],"affiliations":[{"raw_affiliation_string":"Yanbian University,College of Engineering,Yanji,China,133002","institution_ids":["https://openalex.org/I1793135"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046515259","display_name":"Xinghua Lu","orcid":"https://orcid.org/0000-0002-8599-2269"},"institutions":[{"id":"https://openalex.org/I1793135","display_name":"Yanbian University","ror":"https://ror.org/039xnh269","country_code":"CN","type":"education","lineage":["https://openalex.org/I1793135"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinghua Lu","raw_affiliation_strings":["Yanbian University,Integration College,Yanji,China","Integration College, Yanbian University, Yanji, China"],"affiliations":[{"raw_affiliation_string":"Yanbian University,Integration College,Yanji,China","institution_ids":["https://openalex.org/I1793135"]},{"raw_affiliation_string":"Integration College, Yanbian University, Yanji, China","institution_ids":["https://openalex.org/I1793135"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100434198"],"corresponding_institution_ids":["https://openalex.org/I1793135"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18516193,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/computer-science","display_name":"Computer science","score":0.8251760005950928},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6526042819023132},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6243810057640076},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6236943006515503},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5989203453063965},{"id":"https://openalex.org/keywords/parallel-architecture","display_name":"Parallel architecture","score":0.5360081195831299},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.49028947949409485},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4794846475124359},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3992424011230469},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2915515899658203},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.16421833634376526},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09847185015678406}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8251760005950928},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6526042819023132},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6243810057640076},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6236943006515503},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5989203453063965},{"id":"https://openalex.org/C2985918086","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel architecture","level":3,"score":0.5360081195831299},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.49028947949409485},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4794846475124359},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3992424011230469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2915515899658203},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.16421833634376526},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09847185015678406},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cisp-bmei60920.2023.10373253","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cisp-bmei60920.2023.10373253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 16th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320330447","display_name":"Yanbian University","ror":"https://ror.org/039xnh269"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1635512741","https://openalex.org/W1974387177","https://openalex.org/W2048497537","https://openalex.org/W2109000787","https://openalex.org/W2129120544","https://openalex.org/W2151484683","https://openalex.org/W2197404611","https://openalex.org/W2531409750","https://openalex.org/W2791616807","https://openalex.org/W2798365772","https://openalex.org/W2954930777","https://openalex.org/W2995588677","https://openalex.org/W4224933355","https://openalex.org/W4319862255","https://openalex.org/W6731370813","https://openalex.org/W6757632829","https://openalex.org/W6839026989"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484","https://openalex.org/W2373767407","https://openalex.org/W2653598178","https://openalex.org/W3110551121","https://openalex.org/W2747006289","https://openalex.org/W4252682934","https://openalex.org/W2851491717"],"abstract_inverted_index":{"Recently,":[0],"the":[1,43,69],"parallel":[2,52,70],"architecture":[3,71],"combining":[4],"global":[5],"and":[6,54,83],"local":[7],"features":[8],"has":[9],"achieved":[10],"remarkable":[11],"performance":[12,30],"in":[13,47,65,90],"speech":[14,84,88],"recognition":[15],"tasks":[16],".":[17],"Inspired":[18],"by":[19],"this,":[20],"we":[21,41],"propose":[22],"a":[23,51],"VAD":[24,29,74],"method":[25,78],"to":[26,59],"further":[27],"improve":[28],"under":[31],"adverse":[32],"noise":[33],"conditions":[34],"with":[35,50],"low":[36],"signal-to-noise":[37],"ratio":[38],"(SNR).":[39],"Specifically,":[40],"replace":[42],"temporal":[44],"attention":[45],"module":[46],"STAM":[48],"[1]":[49],"structure,":[53],"introduce":[55],"adaptive":[56],"mask":[57],"convolution":[58],"more":[60],"finely":[61],"capture":[62],"vocal":[63],"characteristics":[64],"acoustic":[66,81],"signals.":[67],"With":[68],"tailored":[72],"for":[73],"tasks,":[75],"Our":[76],"SAPVAD":[77],"comprehensively":[79],"captures":[80],"environmental":[82],"features,":[85],"enabling":[86],"accurate":[87],"detection":[89],"noisy":[91],"environments.":[92]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}
