{"id":"https://openalex.org/W2513345070","doi":"https://doi.org/10.21437/interspeech.2016-268","title":"Feature Learning with Raw-Waveform CLDNNs for Voice Activity Detection","display_name":"Feature Learning with Raw-Waveform CLDNNs for Voice Activity Detection","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2513345070","doi":"https://doi.org/10.21437/interspeech.2016-268","mag":"2513345070"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-268","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repositorio.uam.es/bitstream/10486/675731/1/feature_zazo_INTERSPEECH_2016.PDF","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033605288","display_name":"Rub\u00e9n Zazo","orcid":"https://orcid.org/0000-0002-4251-1445"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruben Zazo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050938071","display_name":"Gabor Simko","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabor Simko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090570382","display_name":"Carolina Parada","orcid":"https://orcid.org/0009-0000-7772-4646"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carolina Parada","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":null,"has_fulltext":true,"cited_by_count":106,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3668","last_page":"3672"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9994999766349792,"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/waveform","display_name":"Waveform","score":0.779114305973053},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.694047749042511},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.682244062423706},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5041495561599731},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4840394854545593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.472066193819046},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36281904578208923},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1334734559059143}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.779114305973053},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.694047749042511},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.682244062423706},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5041495561599731},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4840394854545593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.472066193819046},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36281904578208923},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1334734559059143},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2016-268","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},{"id":"pmh:oai:repositorio.uam.es:10486/675731","is_oa":true,"landing_page_url":"http://hdl.handle.net/10486/675731","pdf_url":"https://repositorio.uam.es/bitstream/10486/675731/1/feature_zazo_INTERSPEECH_2016.PDF","source":{"id":"https://openalex.org/S4306400964","display_name":"Biblos-e Archivo (Universidad Aut\u00f3noma de Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63634437","host_organization_name":"Universidad Aut\u00f3noma de Madrid","host_organization_lineage":["https://openalex.org/I63634437"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceObject"}],"best_oa_location":{"id":"pmh:oai:repositorio.uam.es:10486/675731","is_oa":true,"landing_page_url":"http://hdl.handle.net/10486/675731","pdf_url":"https://repositorio.uam.es/bitstream/10486/675731/1/feature_zazo_INTERSPEECH_2016.PDF","source":{"id":"https://openalex.org/S4306400964","display_name":"Biblos-e Archivo (Universidad Aut\u00f3noma de Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63634437","host_organization_name":"Universidad Aut\u00f3noma de Madrid","host_organization_lineage":["https://openalex.org/I63634437"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2513345070.pdf"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1536583098","https://openalex.org/W1600744878","https://openalex.org/W2048497537","https://openalex.org/W2108289863","https://openalex.org/W2112739286","https://openalex.org/W2126693545","https://openalex.org/W2129120544","https://openalex.org/W2143612262","https://openalex.org/W2168231600","https://openalex.org/W2184045248","https://openalex.org/W2259317772","https://openalex.org/W2293634267","https://openalex.org/W2294745040","https://openalex.org/W2295228182","https://openalex.org/W2398826216","https://openalex.org/W2402212287"],"related_works":["https://openalex.org/W2601157893","https://openalex.org/W2373006798","https://openalex.org/W2056912418","https://openalex.org/W2112208972","https://openalex.org/W2123759770","https://openalex.org/W2033213769","https://openalex.org/W2811390910","https://openalex.org/W4312376745","https://openalex.org/W2768048376","https://openalex.org/W2082269393"],"abstract_inverted_index":{"Voice":[0],"Activity":[1],"Detection":[2],"(VAD)":[3],"is":[4,28,55,95,126],"an":[5,29],"important":[6],"preprocessing":[7],"step":[8],"in":[9,145],"any":[10],"state-of-the-art":[11],"speech":[12],"recognition":[13],"system.":[14],"Choosing":[15],"the":[16,71,78,82,90,119,135,150,179,182,186,195],"right":[17],"set":[18],"of":[19,32,114,153,168,181,194],"features":[20,87,188],"and":[21,27,48,121,161,185],"model":[22,49,130,183],"architecture":[23,67],"can":[24],"be":[25],"challenging":[26],"active":[30],"area":[31],"research.":[33],"In":[34,106,175],"this":[35],"paper":[36],"we":[37,177],"propose":[38],"a":[39,58,109,127,166,191],"novel":[40],"approach":[41],"to":[42,44,85,134,165,189],"VAD":[43,132],"tackle":[45],"both":[46,115,159],"feature":[47],"selection":[50],"jointly.":[51],"The":[52,137],"proposed":[53,138,196],"method":[54],"based":[56],"on":[57,158],"CLDNN":[59],"(Convolutional,":[60],"Long":[61],"Short-Term":[62],"Memory,":[63],"Deep":[64],"Neural":[65],"Networks)":[66],"fed":[68],"directly":[69,88],"with":[70,118,124,172],"raw":[72,79],"waveform.":[73],"We":[74],"show":[75],"that":[76],"using":[77,99,108],"waveform":[80],"allows":[81],"neural":[83],"network":[84],"learn":[86],"for":[89,103,131],"task":[91],"at":[92,149],"hand,":[93],"which":[94,111],"more":[96],"powerful":[97],"than":[98],"log-mel":[100,173],"features,":[101],"specially":[102],"noisy":[104,162],"environments.":[105],"addition,":[107,176],"CLDNN,":[110],"takes":[112],"advantage":[113],"frequency":[116],"modeling":[117,123],"CNN":[120],"temporal":[122],"LSTM,":[125],"much":[128],"better":[129,192],"compared":[133,164],"DNN.":[136],"system":[139],"achieves":[140],"over":[141],"78%":[142],"relative":[143],"improvement":[144],"False":[146,155],"Alarms":[147],"(FA)":[148],"operating":[151],"point":[152],"2%":[154],"Rejects":[156],"(FR)":[157],"clean":[160],"conditions":[163],"DNN":[167],"comparable":[169],"size":[170,184],"trained":[171],"features.":[174],"study":[178],"impact":[180],"learned":[187],"provide":[190],"understanding":[193],"architecture.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":7}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2016-09-16T00:00:00"}