{"id":"https://openalex.org/W2403186097","doi":"https://doi.org/10.21437/interspeech.2012-527","title":"Developing a speech activity detection system for the DARPA RATS program","display_name":"Developing a speech activity detection system for the DARPA RATS program","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2403186097","doi":"https://doi.org/10.21437/interspeech.2012-527","mag":"2403186097"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-527","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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/A5110640042","display_name":"Tim Ng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tim Ng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389660","display_name":"Bing Zhang","orcid":"https://orcid.org/0000-0001-7592-1195"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bing Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048517713","display_name":"Long Nguyen","orcid":"https://orcid.org/0000-0002-0884-1635"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034173999","display_name":"Spyros Matsoukas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Spyros Matsoukas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xinhui Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinhui Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033351155","display_name":"Nima Mesgarani","orcid":"https://orcid.org/0000-0002-2987-759X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nima Mesgarani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045351360","display_name":"Karel Vesel\u00fd","orcid":"https://orcid.org/0000-0002-3568-7493"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karel Vesel\u00fd","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076315361","display_name":"Pavel Mat\u011bjka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pavel Mat\u011bjka","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.7121,"has_fulltext":false,"cited_by_count":104,"citation_normalized_percentile":{"value":0.99167822,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1969","last_page":"1972"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6160140633583069},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4689079523086548},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.418364554643631},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3023671805858612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6160140633583069},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4689079523086548},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.418364554643631},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3023671805858612}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2012-527","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W21371201","https://openalex.org/W2090861223","https://openalex.org/W2104448323","https://openalex.org/W2104835909","https://openalex.org/W2130426352","https://openalex.org/W2132214951","https://openalex.org/W2887979278"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W3135230428","https://openalex.org/W2164637175","https://openalex.org/W2099105119","https://openalex.org/W2069501481","https://openalex.org/W2368779261","https://openalex.org/W3002577753","https://openalex.org/W2182174551","https://openalex.org/W2810519502","https://openalex.org/W2539486939"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,11,15,19,34,111],"speech":[4],"activity":[5],"detection":[6,36,105],"(SAD)":[7],"system":[8,114],"developed":[9],"by":[10,74],"Patrol":[12],"team":[13],"for":[14,103,110],"first":[16],"phase":[17],"of":[18,25,33,77,84,113],"DARPA":[20],"RATS":[21],"(Robust":[22],"Automatic":[23],"Transcription":[24],"Speech)":[26],"program,":[27],"which":[28],"seeks":[29],"to":[30,49],"advance":[31],"state":[32],"art":[35],"capabilities":[37],"on":[38,53,60],"audio":[39],"from":[40,107],"highly":[41],"degraded":[42],"communication":[43],"channels.":[44],"We":[45,63,97],"present":[46,99],"two":[47],"approaches":[48],"SAD,":[50],"one":[51,58],"based":[52,59],"Gaussian":[54],"mixture":[55],"models,":[56],"and":[57,93],"multi-layer":[61],"perceptrons.":[62],"show":[64],"that":[65],"significant":[66],"gains":[67],"in":[68],"SAD":[69],"accuracy":[70],"can":[71],"be":[72],"obtained":[73],"careful":[75],"design":[76],"acoustic":[78],"front":[79],"end,":[80],"feature":[81],"normalization,":[82],"incorporation":[83],"long":[85],"span":[86],"features":[87],"via":[88],"data-driven":[89],"dimensionality":[90],"reducing":[91],"transforms,":[92],"channel":[94],"dependent":[95],"modeling.":[96],"also":[98],"a":[100],"novel":[101],"technique":[102],"normalizing":[104],"scores":[106],"different":[108],"systems":[109],"purpose":[112],"combination.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":16},{"year":2013,"cited_by_count":18},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}