{"id":"https://openalex.org/W1536583098","doi":"https://doi.org/10.1109/icassp.2015.7178822","title":"Improvements to the IBM speech activity detection system for the DARPA RATS program","display_name":"Improvements to the IBM speech activity detection system for the DARPA RATS program","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1536583098","doi":"https://doi.org/10.1109/icassp.2015.7178822","mag":"1536583098"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM T.J. Watson Research Center, USA","IBM T. J Watson Research Center, Yorktown Heights, USA"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, USA","institution_ids":[]},{"raw_affiliation_string":"IBM T. J Watson Research Center, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM T.J. Watson Research Center, USA","IBM T. J Watson Research Center, Yorktown Heights, USA"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, USA","institution_ids":[]},{"raw_affiliation_string":"IBM T. J Watson Research Center, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113701682","display_name":"Maarten Van Segbroeck","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maarten Van Segbroeck","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, US","SAIL, University of Southern California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, US","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"SAIL, University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth S. Narayanan","raw_affiliation_strings":["SAIL, University of Southern California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"SAIL, University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101787514"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":11.1274,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.98291144,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4500","last_page":"4504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.998199999332428,"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/ibm-pc-compatible","display_name":"IBM PC compatible","score":0.6148990392684937},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.6086153984069824},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5043438673019409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4914642572402954},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38858699798583984},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.195734441280365},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10216072201728821}],"concepts":[{"id":"https://openalex.org/C77741850","wikidata":"https://www.wikidata.org/wiki/Q751046","display_name":"IBM PC compatible","level":3,"score":0.6148990392684937},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.6086153984069824},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5043438673019409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4914642572402954},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38858699798583984},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.195734441280365},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10216072201728821},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2015.7178822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.719.6215","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.719.6215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.clsp.jhu.edu/%7Esamuel/pdfs/ibm_sad.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W396690109","https://openalex.org/W2004930422","https://openalex.org/W2023582935","https://openalex.org/W2028706510","https://openalex.org/W2052667477","https://openalex.org/W2054139811","https://openalex.org/W2058732030","https://openalex.org/W2085085647","https://openalex.org/W2091425152","https://openalex.org/W2102346872","https://openalex.org/W2109440058","https://openalex.org/W2112796928","https://openalex.org/W2161025448","https://openalex.org/W2170580867","https://openalex.org/W2181395726","https://openalex.org/W2295098554","https://openalex.org/W2401364490","https://openalex.org/W2403186097","https://openalex.org/W2405787239","https://openalex.org/W2406310406","https://openalex.org/W2407934257","https://openalex.org/W2887979278","https://openalex.org/W6613520308","https://openalex.org/W6675700563","https://openalex.org/W6685770725","https://openalex.org/W6697089127","https://openalex.org/W6712995851","https://openalex.org/W6713037448","https://openalex.org/W6713603373","https://openalex.org/W6713623370","https://openalex.org/W6713989789","https://openalex.org/W6753916174"],"related_works":["https://openalex.org/W4245655478","https://openalex.org/W628040712","https://openalex.org/W1974489212","https://openalex.org/W2115322724","https://openalex.org/W2490950126","https://openalex.org/W2145497449","https://openalex.org/W4250790423","https://openalex.org/W4235208381","https://openalex.org/W1565496210","https://openalex.org/W1535371613"],"abstract_inverted_index":{"In":[0],"this":[1,26],"paper":[2],"we":[3],"describe":[4],"improvements":[5,67],"to":[6,77],"the":[7,15,19,48,53,62,84,88,96],"IBM":[8],"speech":[9],"activity":[10],"detection":[11],"(SAD)":[12],"system":[13,51,91],"for":[14],"third":[16],"phase":[17,28,49,80],"of":[18,43,61,68,99,114],"DARPA":[20],"RATS":[21],"program.":[22],"The":[23],"progress":[24],"during":[25],"final":[27,85],"comes":[29],"from":[30],"jointly":[31],"training":[32],"convolutional":[33],"and":[34,72,126],"regular":[35],"deep":[36],"neural":[37],"networks":[38],"with":[39,111],"rich":[40],"time-frequency":[41],"representations":[42],"speech.":[44],"With":[45],"these":[46],"additions,":[47],"3":[50],"reduces":[52],"equal":[54],"error":[55],"rate":[56],"(EER)":[57],"significantly":[58],"on":[59,70,74],"both":[60],"program's":[63],"development":[64],"sets":[65],"(relative":[66],"20%":[69],"dev1":[71],"7%":[73],"dev2)":[75],"compared":[76],"an":[78],"earlier":[79],"2":[81],"system.":[82],"For":[83],"program":[86,97],"evaluation,":[87],"newly":[89],"developed":[90],"also":[92],"performs":[93],"well":[94],"past":[95],"target":[98],"3%":[100,133],"P":[101,107,116,122,128,134],"<inf":[102,108,117,123,129,135],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[103,109,118,124,130,136],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">miss</inf>":[104,119,137],"at":[105,120,132],"1%":[106,121],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">fa</inf>":[110,125,131],"a":[112],"performance":[113],"1.2%":[115],"0.3%":[127],".":[138]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}