{"id":"https://openalex.org/W3007258144","doi":"https://doi.org/10.21437/interspeech.2010-776","title":"Noise robust voice activity detection using features extracted from the time-domain autocorrelation function","display_name":"Noise robust voice activity detection using features extracted from the time-domain autocorrelation function","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W3007258144","doi":"https://doi.org/10.21437/interspeech.2010-776","mag":"3007258144"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-776","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.qut.edu.au/40656/1/2011006688_H_Ghaemmaghami_ePrints.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012849807","display_name":"Houman Ghaemmaghami","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Houman Ghaemmaghami","raw_affiliation_strings":["Queensland University of Technology.,"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology.,","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103337639","display_name":"Brendan Baker","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Brendan Baker","raw_affiliation_strings":["Queensland University of Technology.,"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology.,","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109041704","display_name":"Robert Vogt","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Robert Vogt","raw_affiliation_strings":["Queensland University of Technology.,"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology.,","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055128383","display_name":"Sridha Sridharan","orcid":"https://orcid.org/0000-0003-4316-9001"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sridha Sridharan","raw_affiliation_strings":["Queensland University of Technology.,"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology.,","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012849807"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":1.015,"has_fulltext":true,"cited_by_count":46,"citation_normalized_percentile":{"value":0.78924308,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3118","last_page":"3121"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/autocorrelation","display_name":"Autocorrelation","score":0.8828381299972534},{"id":"https://openalex.org/keywords/autocorrelation-technique","display_name":"Autocorrelation technique","score":0.685029149055481},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6373255252838135},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6299909353256226},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5655288696289062},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.47712254524230957},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.46873173117637634},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.425952672958374},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.42175182700157166},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4165692627429962},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3599141240119934},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23491668701171875},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.20471322536468506},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14991450309753418},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12584102153778076}],"concepts":[{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.8828381299972534},{"id":"https://openalex.org/C183223151","wikidata":"https://www.wikidata.org/wiki/Q4826228","display_name":"Autocorrelation technique","level":3,"score":0.685029149055481},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6373255252838135},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6299909353256226},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5655288696289062},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.47712254524230957},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.46873173117637634},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.425952672958374},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.42175182700157166},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4165692627429962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3599141240119934},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23491668701171875},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.20471322536468506},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14991450309753418},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12584102153778076},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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":2,"locations":[{"id":"doi:10.21437/interspeech.2010-776","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:40656","is_oa":true,"landing_page_url":"http://purl.org/au-research/grants/arc/LP0991238","pdf_url":"https://eprints.qut.edu.au/40656/1/2011006688_H_Ghaemmaghami_ePrints.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 11th Annual Conference of the International Speech Communication Association","raw_type":"Chapter in Book, Report or Conference volume"}],"best_oa_location":{"id":"pmh:oai:eprints.qut.edu.au:40656","is_oa":true,"landing_page_url":"http://purl.org/au-research/grants/arc/LP0991238","pdf_url":"https://eprints.qut.edu.au/40656/1/2011006688_H_Ghaemmaghami_ePrints.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 11th Annual Conference of the International Speech Communication Association","raw_type":"Chapter in Book, Report or Conference volume"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3007258144.pdf"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W36345725","https://openalex.org/W1506438021","https://openalex.org/W2100124793","https://openalex.org/W2119726966","https://openalex.org/W2129120544","https://openalex.org/W2138130935","https://openalex.org/W2141475567","https://openalex.org/W2142773518","https://openalex.org/W2145030715","https://openalex.org/W2161139374","https://openalex.org/W2162969672","https://openalex.org/W2170644918","https://openalex.org/W2535438430","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2941168791","https://openalex.org/W2388176952","https://openalex.org/W2039878594","https://openalex.org/W174653542","https://openalex.org/W2138039466","https://openalex.org/W2029025464","https://openalex.org/W2385206145","https://openalex.org/W2379831147","https://openalex.org/W2381153750","https://openalex.org/W2100384625"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,15,52,66],"method":[4,24],"of":[5,30,40,55,60,68,105,111,132],"voice":[6],"activity":[7],"detection":[8,20],"(VAD)":[9],"for":[10],"high":[11],"noise":[12,16,79],"scenarios,":[13],"using":[14,91,144],"robust":[17],"voiced":[18],"speech":[19],"feature.":[21],"The":[22,33,47,81],"developed":[23],"is":[25,75],"based":[26],"on":[27,139],"the":[28,37,41,61,85,97,112,123,140],"fusion":[29,94],"two":[31,86],"systems.":[32],"first":[34],"system":[35,50,126],"utilises":[36],"maximum":[38],"peak":[39],"normalised":[42,62],"time-domain":[43],"autocorrelation":[44,63,99],"function":[45],"(MaxPeak).":[46],"second":[48],"zone":[49],"uses":[51],"novel":[53],"combination":[54],"cross-correlation":[56],"and":[57,71,114,118],"zero-crossing":[58,100],"rate":[59,101,137],"to":[64,77,95,109,121],"approximate":[65],"measure":[67],"signal":[69],"pitch":[70],"periodicity":[72],"(CrossCorr)":[73],"that":[74],"hypothesised":[76],"be":[78],"robust.":[80],"score":[82],"outputs":[83],"by":[84],"systems":[87],"are":[88],"then":[89],"merged":[90],"weighted":[92],"sum":[93],"create":[96],"proposed":[98],"(AZR)":[102],"VAD.":[103],"Accuracy":[104],"AZR":[106],"was":[107,119],"compared":[108],"state":[110],"art":[113],"standardised":[115],"VAD":[116],"methods":[117],"shown":[120],"outperform":[122],"best":[124],"performing":[125],"with":[127],"an":[128],"average":[129],"relative":[130],"improvement":[131],"24.8%":[133],"in":[134],"half-total":[135],"error":[136],"(HTER)":[138],"QUT-NOISE-TIMIT":[141],"database":[142],"created":[143],"real":[145],"recordings":[146],"from":[147],"high-noise":[148],"environments.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
