{"id":"https://openalex.org/W2403004229","doi":"https://doi.org/10.1109/icassp.2016.7472771","title":"A phonetically aware system for speech activity detection","display_name":"A phonetically aware system for speech activity detection","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2403004229","doi":"https://doi.org/10.1109/icassp.2016.7472771","mag":"2403004229"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5056267912","display_name":"Luciana Ferrer","orcid":"https://orcid.org/0000-0002-0426-8683"},"institutions":[{"id":"https://openalex.org/I151201029","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59","country_code":"AR","type":"government","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I24354313","display_name":"Universidad de Buenos Aires","ror":"https://ror.org/0081fs513","country_code":"AR","type":"education","lineage":["https://openalex.org/I24354313"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Luciana Ferrer","raw_affiliation_strings":["Departamento de Computaci\u00f3n, Universidad de Buenos Aires and CONICET, Argentina"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Computaci\u00f3n, Universidad de Buenos Aires and CONICET, Argentina","institution_ids":["https://openalex.org/I151201029","https://openalex.org/I24354313"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025265147","display_name":"Martin Graciarena","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Graciarena","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, California, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091201226","display_name":"Vikramjit Mitra","orcid":"https://orcid.org/0000-0002-2721-3976"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikramjit Mitra","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, California, USA","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5710","last_page":"5714"},"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":0.9987999796867371,"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":0.8203384876251221},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7302101850509644},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6895042657852173},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6795251965522766},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5611241459846497},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5362735390663147},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.47696006298065186},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4705902636051178},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.41917121410369873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41794759035110474},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.15937462449073792},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06815609335899353}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8203384876251221},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7302101850509644},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6895042657852173},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6795251965522766},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5611241459846497},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5362735390663147},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.47696006298065186},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4705902636051178},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.41917121410369873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41794759035110474},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.15937462449073792},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06815609335899353},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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","display_name":"Peace, Justice and strong institutions","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1528954144","https://openalex.org/W1536583098","https://openalex.org/W1563939609","https://openalex.org/W1600744878","https://openalex.org/W1909308924","https://openalex.org/W1995562189","https://openalex.org/W2153181479","https://openalex.org/W2175575774","https://openalex.org/W2183984815","https://openalex.org/W2185814970","https://openalex.org/W2295098554","https://openalex.org/W2401364490","https://openalex.org/W2403186097","https://openalex.org/W2407934257","https://openalex.org/W2408548175","https://openalex.org/W2887979278","https://openalex.org/W2962853205","https://openalex.org/W6639916541","https://openalex.org/W6685355283","https://openalex.org/W6713037448","https://openalex.org/W6713603373","https://openalex.org/W6714073180","https://openalex.org/W6753916174"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484","https://openalex.org/W2653598178","https://openalex.org/W2373767407","https://openalex.org/W3110551121","https://openalex.org/W2747006289","https://openalex.org/W2131486661","https://openalex.org/W4252682934"],"abstract_inverted_index":{"Speech":[0,51],"activity":[1],"detection":[2],"(SAD)":[3],"is":[4,107],"an":[5],"essential":[6],"component":[7],"of":[8,18,39,50,163],"most":[9],"speech":[10],"processing":[11],"tasks":[12],"and":[13,22,143],"greatly":[14],"influences":[15],"the":[16,19,45,58,92,101,117,132,150,154,157,177],"performance":[17,137,182],"systems.":[20,30,99],"Noise":[21],"channel":[23],"distortions":[24],"remain":[25],"a":[26,37,79,104,126],"challenge":[27],"for":[28,74,112],"SAD":[29,84,172],"In":[31,100],"this":[32,55],"paper,":[33],"we":[34],"focus":[35],"on":[36,64,138],"dataset":[38],"highly":[40],"degraded":[41],"signals,":[42],"developed":[43],"under":[44],"DARPA":[46],"Robust":[47],"Automatic":[48],"Transcription":[49],"(RATS)":[52],"program.":[53],"On":[54,153,174],"challenging":[56],"data,":[57],"best-performing":[59],"systems":[60],"are":[61,120],"those":[62,148],"based":[63],"deep":[65],"neural":[66],"networks":[67],"(DNN)":[68],"trained":[69,108,129],"to":[70,83,87,109,125,130,147,161,167,183,190,193,196],"predict":[71,110,131],"speech/non-speech":[72,133],"posteriors":[73,111],"each":[75],"frame.":[76],"We":[77,135],"propose":[78],"novel":[80],"two-stage":[81],"approach":[82,159],"that":[85],"attempts":[86],"model":[88],"phonetic":[89],"information":[90],"in":[91,97,149],"signal":[93],"more":[94,187],"explicitly":[95],"than":[96],"current":[98],"first":[102],"stage,":[103],"bottleneck":[105,118],"DNN":[106,171],"senones.":[113],"The":[114],"activations":[115],"at":[116],"layer":[119],"then":[121],"used":[122],"as":[123],"input":[124],"second":[127],"DNN,":[128],"posteriors.":[134],"test":[136],"two":[139],"datasets,":[140],"with":[141],"matched":[142,155],"mismatched":[144,175,197],"channels":[145],"compared":[146],"training":[151],"data.":[152,198],"channels,":[156,176],"proposed":[158,178],"leads":[160],"gains":[162],"approximately":[164],"35%":[165],"relative":[166],"our":[168,184],"best":[169],"single-stage":[170],"system.":[173],"system":[179],"obtains":[180],"comparable":[181],"baseline,":[185],"indicating":[186],"work":[188],"needs":[189],"be":[191],"done":[192],"improve":[194],"robustness":[195]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}