{"id":"https://openalex.org/W2891887878","doi":"https://doi.org/10.1109/icassp.2018.8462482","title":"Use of Pitch Continuity for Robust Speech Activity Detection","display_name":"Use of Pitch Continuity for Robust Speech Activity Detection","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891887878","doi":"https://doi.org/10.1109/icassp.2018.8462482","mag":"2891887878"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5078423590","display_name":"Yiwen Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiwen Shao","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103431069","display_name":"Qiguang Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiguang Lin","raw_affiliation_strings":["Baihu Technology Co.,Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baihu Technology Co.,Ltd., China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0824,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.784276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"10","issue":null,"first_page":"5534","last_page":"5538"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.652230978012085},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6011223793029785},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.5869460105895996},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45446035265922546},{"id":"https://openalex.org/keywords/activity-detection","display_name":"Activity detection","score":0.41630274057388306},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36707329750061035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23561453819274902}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.652230978012085},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6011223793029785},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.5869460105895996},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45446035265922546},{"id":"https://openalex.org/C2988656282","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity detection","level":2,"score":0.41630274057388306},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36707329750061035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23561453819274902}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W169745891","https://openalex.org/W1604034532","https://openalex.org/W1974387177","https://openalex.org/W2023582935","https://openalex.org/W2107831318","https://openalex.org/W2118049600","https://openalex.org/W2295098554","https://openalex.org/W2295228182","https://openalex.org/W3127686677","https://openalex.org/W4297989434","https://openalex.org/W6676245417","https://openalex.org/W6677597873","https://openalex.org/W6697089127","https://openalex.org/W6697318802","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2149528081","https://openalex.org/W2165935979","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2131711534","https://openalex.org/W2349264490","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Speech":[0],"activity":[1],"detection":[2],"(SAD)":[3],"is":[4,55,105],"an":[5,131],"important":[6],"component":[7],"for":[8],"various":[9,108],"speech":[10],"processing":[11],"applications":[12],"and":[13,67,94,154],"has":[14,28],"been":[15],"researched":[16],"extensively":[17],"recently.":[18],"The":[19,101,118],"pitch":[20,49,75,82,92,163],"continuity,":[21],"a":[22,32,43,146],"significant":[23],"characteristic":[24],"of":[25,110,149,162],"speech,":[26],"however,":[27],"not":[29],"successfully":[30],"played":[31],"role":[33],"in":[34,97],"existing":[35],"SAD":[36,128],"methods.":[37],"In":[38],"this":[39],"work,":[40],"we":[41],"propose":[42],"novel":[44,147],"way":[45],"to":[46,81,126,133,141],"integrate":[47],"the":[48,59,73,77,90,98,122,150,160],"continuity":[50],"with":[51,107],"pitch-related":[52],"features.":[53],"Practice":[54],"carried":[56],"out":[57],"through":[58],"Combo-SAD":[60],"approach:":[61],"We":[62,143],"examine":[63],"three":[64],"consecutive":[65],"frames":[66],"assume":[68],"that":[69,121],"they":[70],"all":[71],"have":[72],"same":[74],"as":[76],"center":[78],"frame":[79],"due":[80],"continuity.":[83],"Corresponding":[84],"feature":[85,104,124],"values":[86],"are":[87],"recomputed":[88],"at":[89,113],"adjusted":[91],"location":[93],"then":[95],"used":[96],"final":[99],"expression.":[100],"new":[102,123],"combo":[103],"evaluated":[106],"types":[109],"additive":[111],"noise":[112],"different":[114],"signal-to-noise":[115],"ratios":[116],"(SNR).":[117],"results":[119],"show":[120],"leads":[125],"better":[127],"performance":[129],"(with":[130],"up":[132],"39.3%":[134],"relative":[135],"improvement":[136],"on":[137],"miss":[138],"rate":[139],"compared":[140],"Combo-SAD).":[142],"also":[144],"introduce":[145],"variant":[148],"underlying":[151],"autocorrelation":[152],"function":[153],"illustrate":[155],"how":[156],"it":[157],"can":[158],"improve":[159],"accuracy":[161],"detection.":[164]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
