{"id":"https://openalex.org/W2954461214","doi":"https://doi.org/10.21437/interspeech.2019-1354","title":"Two-Dimensional Convolutional Recurrent Neural Networks for Speech Activity Detection","display_name":"Two-Dimensional Convolutional Recurrent Neural Networks for Speech Activity Detection","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2954461214","doi":"https://doi.org/10.21437/interspeech.2019-1354","mag":"2954461214"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1354","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.dora.dmu.ac.uk/handle/2086/18174","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007136125","display_name":"Anastasios Vafeiadis","orcid":"https://orcid.org/0000-0003-1102-5708"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Anastasios Vafeiadis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085087454","display_name":"Eleftherios Fanioudakis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eleftherios Fanioudakis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050529028","display_name":"Ilyas Potamitis","orcid":"https://orcid.org/0000-0002-7111-3331"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ilyas Potamitis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064307246","display_name":"Konstantinos Votis","orcid":"https://orcid.org/0000-0001-6381-8326"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konstantinos Votis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000523843","display_name":"Dimitrios Giakoumis","orcid":"https://orcid.org/0000-0003-1844-186X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dimitrios Giakoumis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087452615","display_name":"Dimitrios Tzovaras","orcid":"https://orcid.org/0000-0001-6915-6722"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dimitrios Tzovaras","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443536","display_name":"Liming Chen","orcid":"https://orcid.org/0000-0003-0200-7989"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liming Chen","raw_affiliation_strings":["School of Computing"],"affiliations":[{"raw_affiliation_string":"School of Computing","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025449942","display_name":"Raouf Hamzaoui","orcid":"https://orcid.org/0000-0001-6699-7331"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raouf Hamzaoui","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5007136125"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5051,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.937074,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2045","last_page":"2049"},"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":0.9994999766349792,"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":0.7402079105377197},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6942340135574341},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5725491046905518},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5455115437507629},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45277151465415955},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3209410011768341},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.28443488478660583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7402079105377197},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6942340135574341},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5725491046905518},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5455115437507629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45277151465415955},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3209410011768341},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28443488478660583}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2019-1354","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:dora.dmu.ac.uk:2086/18174","is_oa":true,"landing_page_url":"https://www.dora.dmu.ac.uk/handle/2086/18174","pdf_url":null,"source":{"id":"https://openalex.org/S4306400394","display_name":"DMU Open Research Archive (De Montfort University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66943878","host_organization_name":"De Montfort University","host_organization_lineage":["https://openalex.org/I66943878"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference"}],"best_oa_location":{"id":"pmh:oai:dora.dmu.ac.uk:2086/18174","is_oa":true,"landing_page_url":"https://www.dora.dmu.ac.uk/handle/2086/18174","pdf_url":null,"source":{"id":"https://openalex.org/S4306400394","display_name":"DMU Open Research Archive (De Montfort University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66943878","host_organization_name":"De Montfort University","host_organization_lineage":["https://openalex.org/I66943878"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1501620","https://openalex.org/W2048497537","https://openalex.org/W2115717467","https://openalex.org/W2116251645","https://openalex.org/W2118354544","https://openalex.org/W2121894251","https://openalex.org/W2121973264","https://openalex.org/W2126693545","https://openalex.org/W2140348518","https://openalex.org/W2147673285","https://openalex.org/W2289394825","https://openalex.org/W2295098554","https://openalex.org/W2403186097","https://openalex.org/W2551314165","https://openalex.org/W2638067502","https://openalex.org/W2738707637","https://openalex.org/W2767895109","https://openalex.org/W2801018181","https://openalex.org/W2912003438","https://openalex.org/W2916979304","https://openalex.org/W2924746379","https://openalex.org/W2949117887","https://openalex.org/W2964121744","https://openalex.org/W3007258144"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W3034302643","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W2964335273","https://openalex.org/W2578422401","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Speech":[0],"Activity":[1],"Detection":[2],"(SAD)":[3],"plays":[4],"an":[5],"important":[6],"role":[7],"in":[8,75,86],"mobile":[9],"communications":[10],"and":[11,63,90],"automatic":[12],"speech":[13],"recognition":[14],"(ASR).":[15],"Developing":[16],"efficient":[17],"SAD":[18,39],"systems":[19],"for":[20],"real-world":[21],"applications":[22],"is":[23],"a":[24,35,45,67,81,91,95,119,126,135],"challenging":[25],"task":[26],"due":[27],"to":[28,38,99],"the":[29,53,87,104,111,130,141,145],"presence":[30],"of":[31,107,110,124,138,144],"noise.":[32],"We":[33],"propose":[34],"new":[36],"approach":[37],"where":[40],"we":[41,56],"treat":[42],"it":[43,133],"as":[44,94],"two-dimensional":[46],"multilabel":[47],"image":[48,76],"classification":[49],"problem.":[50],"To":[51],"classify":[52,64],"audio":[54],"segments,":[55],"compute":[57],"their":[58],"Short-time":[59],"Fourier":[60],"Transform":[61],"spectrograms":[62],"them":[65],"with":[66],"Convolutional":[68],"Recurrent":[69],"Neural":[70],"Network":[71],"(CRNN),":[72],"traditionally":[73],"used":[74],"recognition.":[77],"Our":[78],"CRNN":[79],"uses":[80],"sigmoid":[82],"activation":[83],"function,":[84],"max-pooling":[85],"frequency":[88],"domain,":[89],"convolutional":[92],"operation":[93],"moving":[96],"average":[97],"filter":[98],"remove":[100],"misclassified":[101],"spikes.":[102],"On":[103],"development":[105],"set":[106],"Task":[108],"1":[109],"2019":[112],"Fearless":[113],"Steps":[114],"Challenge,":[115],"our":[116],"system":[117],"achieved":[118,134],"decision":[120],"cost":[121],"function":[122],"(DCF)":[123],"2.89%,":[125],"66.4%":[127],"improvement":[128],"over":[129],"baseline.":[131],"Moreover,":[132],"DCF":[136],"score":[137],"3.318%":[139],"on":[140],"evaluation":[142],"dataset":[143],"challenge,":[146],"ranking":[147],"first":[148],"among":[149],"all":[150],"submissions.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":8}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}