{"id":"https://openalex.org/W4416250898","doi":"https://doi.org/10.1109/waspaa66052.2025.11230931","title":"Robust Speech Activity Detection in the Presence of Singing Voice","display_name":"Robust Speech Activity Detection in the Presence of Singing Voice","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250898","doi":"https://doi.org/10.1109/waspaa66052.2025.11230931"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230931","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230931","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.09713","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116591583","display_name":"Philipp Grundhuber","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Philipp Grundhuber","raw_affiliation_strings":["Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008815790","display_name":"Mhd Modar Halimeh","orcid":"https://orcid.org/0000-0001-6113-3067"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mhd Modar Halimeh","raw_affiliation_strings":["Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050706599","display_name":"M. Strauss","orcid":"https://orcid.org/0000-0003-0610-8250"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Strau\u00df","raw_affiliation_strings":["Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031626756","display_name":"Emanu\u00ebl A. P. Habets","orcid":"https://orcid.org/0000-0002-2613-8046"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Emanu\u00ebl A. P. Habets","raw_affiliation_strings":["International Audio Laboratories,Erlangen,Germany"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories,Erlangen,Germany","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5116591583"],"corresponding_institution_ids":["https://openalex.org/I4210124274"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44303071,"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/T10860","display_name":"Speech and Audio Processing","score":0.9420999884605408,"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":0.9420999884605408,"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":0.01720000058412552,"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/T10863","display_name":"Voice and Speech Disorders","score":0.009700000286102295,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7099000215530396},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6859999895095825},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5439000129699707},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4903999865055084},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.47999998927116394},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4652000069618225},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.40709999203681946},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38440001010894775}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7305999994277954},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7224000096321106},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7099000215530396},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6859999895095825},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5439000129699707},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4903999865055084},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.47999998927116394},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45100000500679016},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.40709999203681946},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2921000123023987},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C2988656282","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity detection","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27630001306533813},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230931","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230931","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.09713","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.09713","pdf_url":"https://arxiv.org/pdf/2512.09713","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:publica.fraunhofer.de:publica/504859","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/504859","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.09713","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.09713","pdf_url":"https://arxiv.org/pdf/2512.09713","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416250898.pdf"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2007664495","https://openalex.org/W2033573285","https://openalex.org/W2179575720","https://openalex.org/W2963868408","https://openalex.org/W2964819890","https://openalex.org/W2972541922","https://openalex.org/W2995588677","https://openalex.org/W3024869864","https://openalex.org/W3056518849","https://openalex.org/W3139270985","https://openalex.org/W3197042120","https://openalex.org/W4224293426","https://openalex.org/W4285106251","https://openalex.org/W4285222490","https://openalex.org/W4392903478","https://openalex.org/W4392904540","https://openalex.org/W4396943642","https://openalex.org/W4402112435","https://openalex.org/W4402980268","https://openalex.org/W4405844975"],"related_works":[],"abstract_inverted_index":{"Speech":[0,27],"Activity":[1,28],"Detection":[2,29],"(SAD)":[3],"systems":[4],"often":[5],"misclassify":[6],"singing":[7,58],"as":[8,17],"speech,":[9],"leading":[10],"to":[11,35,60,83,117],"degraded":[12],"performance":[13,71],"in":[14,39,87,128],"applications":[15],"such":[16],"dialogue":[18],"enhancement":[19],"and":[20,57,76,121],"automatic":[21],"speech":[22,38,56,105,120],"recognition.":[23],"We":[24],"introduce":[25],"Singing-Robust":[26],"(SR-SAD),":[30],"a":[31,49,64,78,93],"neural":[32],"network":[33],"designed":[34],"robustly":[36],"detect":[37],"the":[40],"presence":[41],"of":[42,55],"singing.":[43,113],"Our":[44],"key":[45],"contributions":[46],"are:":[47],"i)":[48],"training":[50],"strategy":[51],"using":[52],"controlled":[53],"ratios":[54],"samples":[59],"improve":[61],"discrimination,":[62],"ii)":[63],"computationally":[65],"efficient":[66],"model":[67],"that":[68,101],"maintains":[69,103],"robust":[70],"while":[72,111],"reducing":[73],"inference":[74],"runtime,":[75],"iii)":[77],"new":[79],"evaluation":[80],"metric":[81],"tailored":[82],"assess":[84],"SAD":[85,127],"robustness":[86],"mixed":[88,129],"speech-singing":[89,130],"scenarios.":[90,131],"Experiments":[91],"on":[92],"challenging":[94],"dataset":[95],"spanning":[96],"multiple":[97],"musical":[98],"genres":[99],"show":[100],"SR-SAD":[102,123],"high":[104],"detection":[106],"accuracy":[107],"(AUC":[108],"=":[109],"0.919)":[110],"rejecting":[112],"By":[114],"explicitly":[115],"learning":[116],"distinguish":[118],"between":[119],"singing,":[122],"enables":[124],"more":[125],"reliable":[126]},"counts_by_year":[],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-11-14T00:00:00"}