{"id":"https://openalex.org/W2059203007","doi":"https://doi.org/10.1109/icassp.2014.6854054","title":"Analyzing convolutional neural networks for speech activity detection in mismatched acoustic conditions","display_name":"Analyzing convolutional neural networks for speech activity detection in mismatched acoustic conditions","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2059203007","doi":"https://doi.org/10.1109/icassp.2014.6854054","mag":"2059203007"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002536077","display_name":"Sriram Ganapathy","orcid":"https://orcid.org/0000-0002-5779-9066"},"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"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Ganapathy","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","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"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010878109","display_name":"Hagen Soltau","orcid":null},"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"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hagen Soltau","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101787514"],"corresponding_institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":5.5938,"has_fulltext":false,"cited_by_count":101,"citation_normalized_percentile":{"value":0.96584364,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2519","last_page":"2523"},"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":0.9998999834060669,"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":0.9997000098228455,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7864265441894531},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7390843629837036},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7313558459281921},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5383774638175964},{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.515191912651062},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5108263492584229},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48734912276268005},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.47832250595092773},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.458989679813385},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4196930229663849},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4099636375904083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4052659869194031},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.30416277050971985},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08324971795082092}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7864265441894531},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7390843629837036},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7313558459281921},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5383774638175964},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.515191912651062},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5108263492584229},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48734912276268005},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.47832250595092773},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.458989679813385},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4196930229663849},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4099636375904083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4052659869194031},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30416277050971985},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08324971795082092},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2014.6854054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.701.2266","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.701.2266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://clsp.jhu.edu/%7Esriram/papers/papers/cnn.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W15516501","https://openalex.org/W1537275613","https://openalex.org/W1967332585","https://openalex.org/W2032362923","https://openalex.org/W2080005694","https://openalex.org/W2087006792","https://openalex.org/W2090861223","https://openalex.org/W2101596234","https://openalex.org/W2112739286","https://openalex.org/W2112796928","https://openalex.org/W2130426352","https://openalex.org/W2132214951","https://openalex.org/W2134557905","https://openalex.org/W2148154194","https://openalex.org/W2155273149","https://openalex.org/W2170644918","https://openalex.org/W2181395726","https://openalex.org/W2295098554","https://openalex.org/W2401364490","https://openalex.org/W2403186097","https://openalex.org/W2403731734","https://openalex.org/W2405787239","https://openalex.org/W2406310406","https://openalex.org/W2887979278","https://openalex.org/W3141736179","https://openalex.org/W6675280436","https://openalex.org/W6685301991","https://openalex.org/W6685770725","https://openalex.org/W6697089127","https://openalex.org/W6712995851","https://openalex.org/W6713037448","https://openalex.org/W6713623370","https://openalex.org/W6713989789","https://openalex.org/W6753916174"],"related_works":["https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2069501481","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W2103239478","https://openalex.org/W2921005841","https://openalex.org/W642007152","https://openalex.org/W2341426843","https://openalex.org/W2131711534"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1,8],"networks":[2,9],"(CNN)":[3],"are":[4,12,28,50],"extensions":[5],"to":[6,71,105,125],"deep":[7],"(DNN)":[10],"which":[11],"used":[13,29],"as":[14,30],"alternate":[15],"acoustic":[16,31,114,143],"models":[17,32,49,118],"with":[18],"state-of-the-art":[19],"performances":[20],"for":[21,33,142],"speech":[22,34],"recognition.":[23],"In":[24,112],"this":[25,69],"paper,":[26],"CNNs":[27,134],"activity":[35],"detection":[36],"(SAD)":[37],"on":[38,52],"data":[39,95],"collected":[40],"over":[41],"noisy":[42],"radio":[43,56],"communication":[44],"channels.":[45],"When":[46],"these":[47,146],"SAD":[48,110,128],"tested":[51],"audio":[53],"recorded":[54],"from":[55,96],"channels":[57],"not":[58],"seen":[59],"during":[60],"training,":[61],"there":[62],"is":[63],"severe":[64],"performance":[65],"degradation.":[66],"We":[67],"attribute":[68],"degradation":[70],"mismatches":[72],"between":[73],"the":[74,80,85,97,100,116],"two":[75],"dimensional":[76],"filters":[77,101],"learnt":[78],"in":[79,109,139,145],"initial":[81],"CNN":[82],"layers":[83],"and":[84],"novel":[86,98],"channel":[87],"data.":[88],"Using":[89],"a":[90,136],"small":[91],"amount":[92],"of":[93],"supervised":[94],"channels,":[99],"can":[102],"be":[103],"adapted":[104,117],"provide":[106,119],"significant":[107,120],"improvements":[108,121],"performance.":[111],"mismatched":[113],"conditions,":[115],"(about":[122],"10-25%)":[123],"relative":[124],"conventional":[126],"DNN-based":[127],"systems.":[129],"These":[130],"results":[131],"illustrate":[132],"that":[133],"have":[135],"considerable":[137],"advantage":[138],"fast":[140],"adaptation":[141],"modeling":[144],"settings.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}