{"id":"https://openalex.org/W4406858928","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848640","title":"Performance Optimization in the Cascade of VAD and ASR Systems: A Study on Evaluation and Alignment Strategies","display_name":"Performance Optimization in the Cascade of VAD and ASR Systems: A Study on Evaluation and Alignment Strategies","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858928","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848640"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5069471244","display_name":"Zhentao Lin","orcid":"https://orcid.org/0000-0003-1977-2249"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhentao Lin","raw_affiliation_strings":["Guangdong University of Technology School,Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology School,Computer Science and Engineering","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341615","display_name":"Zhihao Chen","orcid":"https://orcid.org/0000-0002-5573-5237"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Chen","raw_affiliation_strings":["Guangdong University of Technology School,Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology School,Computer Science and Engineering","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073040865","display_name":"Bi Zeng","orcid":"https://orcid.org/0000-0001-8596-8333"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bi Zeng","raw_affiliation_strings":["Guangdong University of Technology School,Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology School,Computer Science and Engineering","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060566993","display_name":"L. Chen","orcid":"https://orcid.org/0000-0001-9246-3691"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leqi Chen","raw_affiliation_strings":["Guangdong University of Technology School,Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology School,Computer Science and Engineering","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100301492","display_name":"Jia Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113818","display_name":"China Electronic Product Reliability and Environmental Test Institute","ror":"https://ror.org/01f4k3b46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210113818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Cai","raw_affiliation_strings":["China Electronic Product Reliability and Environmental Testing Research Institute"],"affiliations":[{"raw_affiliation_string":"China Electronic Product Reliability and Environmental Testing Research Institute","institution_ids":["https://openalex.org/I4210113818"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5069471244"],"corresponding_institution_ids":["https://openalex.org/I139024713"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24670186,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.3628999888896942,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.3628999888896942,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.793513298034668},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7039616107940674},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4023613929748535},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17453265190124512}],"concepts":[{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.793513298034668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7039616107940674},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4023613929748535},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17453265190124512},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10848640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2051572649","https://openalex.org/W2069095950","https://openalex.org/W2406226915","https://openalex.org/W2408468399","https://openalex.org/W2885195348","https://openalex.org/W2963308316","https://openalex.org/W3197478142","https://openalex.org/W3198109792","https://openalex.org/W4283067311","https://openalex.org/W4296068805","https://openalex.org/W4319586585","https://openalex.org/W4400434308"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2153719181","https://openalex.org/W1971748923","https://openalex.org/W1566155057","https://openalex.org/W2060986072","https://openalex.org/W2052574922","https://openalex.org/W64588465","https://openalex.org/W3120641340"],"abstract_inverted_index":{"Voice":[0],"Activity":[1],"Detection":[2],"(VAD)":[3],"is":[4,30],"a":[5,53,75,119],"critical":[6],"pre-processing":[7],"step":[8],"in":[9,22,65],"Automatic":[10],"Speech":[11],"Recognition":[12],"(ASR)":[13],"systems,":[14],"tasked":[15],"with":[16,45],"distinguishing":[17],"speech":[18,103],"from":[19,101,126],"non-speech":[20,95],"segments":[21],"audio":[23],"signals.":[24],"The":[25,72],"accuracy":[26],"of":[27,63,142],"this":[28],"segmentation":[29],"essential,":[31],"as":[32,96,104],"errors":[33,83],"can":[34],"significantly":[35],"impair":[36],"ASR":[37,46,64,145],"performance.":[38],"This":[39],"study":[40],"integrates":[41],"multiple":[42],"VAD":[43,93,143,151],"algorithms":[44],"systems":[47],"and":[48,70,81,84,153],"examines":[49],"their":[50],"interplay":[51],"through":[52],"chapter-level":[54],"analysis,":[55],"focusing":[56],"on":[57,123,144],"the":[58,112,127,140],"Word":[59,115],"Error":[60,116],"Rate":[61,117],"(WER)":[62],"relation":[66],"to":[67,92],"VAD\u2019s":[68,85],"recall":[69],"precision.":[71],"research":[73],"reveals":[74],"strong":[76],"correlation":[77],"between":[78,150],"ASR\u2019s":[79],"insertion":[80],"deletion":[82],"performance":[86],"metrics.":[87],"Insertions":[88],"are":[89],"mainly":[90],"due":[91],"misclassifying":[94,102],"speech,":[97],"while":[98],"deletions":[99],"stem":[100],"non-speech.":[105],"To":[106],"address":[107],"these":[108],"issues,":[109],"we":[110],"introduce":[111],"Aligned":[113],"Token":[114],"(atWER),":[118],"novel":[120],"metric":[121],"based":[122],"forced":[124],"alignment":[125],"Connectionist":[128],"Temporal":[129],"Classification":[130],"(CTC)":[131],"framework.":[132],"Our":[133],"experiments":[134],"show":[135],"that":[136],"atWER":[137],"accurately":[138],"reflects":[139],"impact":[141],"performance,":[146],"effectively":[147],"reducing":[148],"discrepancies":[149],"annotations":[152],"classification":[154],"outcomes.":[155]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}