{"id":"https://openalex.org/W4319862673","doi":"https://doi.org/10.1109/slt54892.2023.10022462","title":"Investigating the Important Temporal Modulations for Deep-Learning-Based Speech Activity Detection","display_name":"Investigating the Important Temporal Modulations for Deep-Learning-Based Speech Activity Detection","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862673","doi":"https://doi.org/10.1109/slt54892.2023.10022462"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022462","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022462","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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 Spoken Language Technology Workshop (SLT)","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/A5109404932","display_name":"Tyler Vuong","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tyler Vuong","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering,USA","Department of Electrical and Computer Engineering, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009315199","display_name":"Nikhil Madaan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikhil Madaan","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering,USA","Department of Electrical and Computer Engineering, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058974480","display_name":"Rohan Panda","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohan Panda","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering,USA","Department of Electrical and Computer Engineering, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069424860","display_name":"Richard M. Stern","orcid":"https://orcid.org/0000-0003-0557-7282"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard M. Stern","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering,USA","Language Technologies Institute, Carnegie Mellon University, USA","Department of Electrical and Computer Engineering, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109404932"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0427,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"525","last_page":"531"},"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":0.9988999962806702,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/spectrogram","display_name":"Spectrogram","score":0.9766288995742798},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6944603323936462},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6159829497337341},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.5804941654205322},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.54557865858078},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.49252089858055115},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4801201820373535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47444188594818115},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.47407880425453186},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46652254462242126},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4601188004016876},{"id":"https://openalex.org/keywords/band-pass-filter","display_name":"Band-pass filter","score":0.45273441076278687},{"id":"https://openalex.org/keywords/amplitude-modulation","display_name":"Amplitude modulation","score":0.4441920220851898},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44284921884536743},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4308960437774658},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38276538252830505},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.202409029006958},{"id":"https://openalex.org/keywords/radio-frequency","display_name":"Radio frequency","score":0.1720157265663147},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12509948015213013},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10331040620803833},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.099945068359375},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.09199276566505432},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08085522055625916}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9766288995742798},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6944603323936462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6159829497337341},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.5804941654205322},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.54557865858078},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.49252089858055115},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4801201820373535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47444188594818115},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.47407880425453186},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46652254462242126},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4601188004016876},{"id":"https://openalex.org/C147788027","wikidata":"https://www.wikidata.org/wiki/Q2718101","display_name":"Band-pass filter","level":2,"score":0.45273441076278687},{"id":"https://openalex.org/C201905106","wikidata":"https://www.wikidata.org/wiki/Q183755","display_name":"Amplitude modulation","level":4,"score":0.4441920220851898},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44284921884536743},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4308960437774658},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38276538252830505},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.202409029006958},{"id":"https://openalex.org/C74064498","wikidata":"https://www.wikidata.org/wiki/Q3396184","display_name":"Radio frequency","level":2,"score":0.1720157265663147},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12509948015213013},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10331040620803833},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.099945068359375},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.09199276566505432},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08085522055625916},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022462","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022462","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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 Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W62903643","https://openalex.org/W97348585","https://openalex.org/W569478347","https://openalex.org/W1992272902","https://openalex.org/W1999454387","https://openalex.org/W2075012882","https://openalex.org/W2130426352","https://openalex.org/W2181253919","https://openalex.org/W2401264858","https://openalex.org/W2588767398","https://openalex.org/W2794209590","https://openalex.org/W2889041236","https://openalex.org/W2964052309","https://openalex.org/W2972869740","https://openalex.org/W3092967725","https://openalex.org/W3096994581","https://openalex.org/W3097629653","https://openalex.org/W3097636940","https://openalex.org/W3104896896","https://openalex.org/W3161003723","https://openalex.org/W3167533889","https://openalex.org/W3197479203","https://openalex.org/W6631190155","https://openalex.org/W6789403026"],"related_works":["https://openalex.org/W1889291648","https://openalex.org/W335396218","https://openalex.org/W2533590149","https://openalex.org/W1504214173","https://openalex.org/W1946395172","https://openalex.org/W1600447354","https://openalex.org/W2602361891","https://openalex.org/W2107964963","https://openalex.org/W2035480840","https://openalex.org/W2052872496"],"abstract_inverted_index":{"We":[0,22],"describe":[1],"a":[2,41,46],"learnable":[3,24,47,106],"modulation":[4,25,90,107,117],"spectrogram":[5,26,108,118],"feature":[6,109],"for":[7,76,95],"speech":[8,99],"activity":[9],"detection":[10],"(SAD).":[11],"Modulation":[12],"features":[13,27,119],"capture":[14],"the":[15,31,57,70,105,112,121],"temporal":[16,67,89],"dynamics":[17],"of":[18],"each":[19,37],"frequency":[20,38],"subband.":[21],"compute":[23],"by":[28],"first":[29],"calculating":[30],"log-mel":[32,114],"spectrogram.":[33],"Next,":[34],"we":[35,102],"filter":[36,43],"subband":[39],"with":[40,83],"bandpass":[42],"that":[44,66,86,104],"contains":[45],"center":[48],"frequency.":[49],"The":[50],"resulting":[51],"SAD":[52,61,125],"system":[53],"was":[54],"evaluated":[55],"on":[56,120],"Fearless":[58,122],"Steps":[59,123],"Phase-04":[60,124],"challenge.":[62],"Experimental":[63],"results":[64,81],"showed":[65],"modulations":[68],"around":[69],"4\u20136":[71],"Hz":[72],"range":[73],"are":[74],"crucial":[75],"deep-learning-based":[77],"SAD.":[78],"These":[79],"experimental":[80],"align":[82],"previous":[84],"studies":[85],"found":[87,103],"slow":[88],"to":[91],"be":[92],"most":[93],"important":[94],"speech-processing":[96],"tasks":[97],"and":[98,115],"intelligibility.":[100],"Additionally,":[101],"outperforms":[110],"both":[111],"standard":[113],"fixed":[116],"test":[126],"set.":[127]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-24T08:33:08.758527","created_date":"2025-10-10T00:00:00"}