{"id":"https://openalex.org/W3011405319","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023101","title":"Joint Training ResCNN-based Voice Activity Detection with Speech Enhancement","display_name":"Joint Training ResCNN-based Voice Activity Detection with Speech Enhancement","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011405319","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023101","mag":"3011405319"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5047523272","display_name":"Tianjiao Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianjiao Xu","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Hohhot, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108035744","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0002-6146-1535"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Hohhot, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Hohhot, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047523272"],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":1.3269,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.82220449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1157","last_page":"1162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9990000128746033,"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/joint","display_name":"Joint (building)","score":0.7392893433570862},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7024198174476624},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6916405558586121},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6560643911361694},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5914087295532227},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5718457698822021},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37016868591308594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2994275689125061},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.108239084482193},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.10441741347312927}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7392893433570862},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7024198174476624},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6916405558586121},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6560643911361694},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5914087295532227},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5718457698822021},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37016868591308594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2994275689125061},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.108239084482193},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10441741347312927},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1974387177","https://openalex.org/W1985242443","https://openalex.org/W1999454387","https://openalex.org/W2006129368","https://openalex.org/W2048497537","https://openalex.org/W2059203007","https://openalex.org/W2078528584","https://openalex.org/W2129120544","https://openalex.org/W2157825442","https://openalex.org/W2194775991","https://openalex.org/W2197404611","https://openalex.org/W2396495723","https://openalex.org/W2513345070","https://openalex.org/W2559260703","https://openalex.org/W2605589342","https://openalex.org/W2612770767","https://openalex.org/W2797121075","https://openalex.org/W2889224635","https://openalex.org/W2889442120","https://openalex.org/W2891433113","https://openalex.org/W2892300106","https://openalex.org/W2949935872","https://openalex.org/W3127686677","https://openalex.org/W6712515972","https://openalex.org/W6789826613"],"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":{"Voice":[0],"activity":[1],"detection":[2],"(VAD)":[3],"is":[4,15,59,119],"considered":[5],"as":[6],"a":[7,17,40,48,83],"solved":[8],"problem":[9],"in":[10,20,35,132],"noise-free":[11],"condition,":[12],"but":[13],"it":[14],"still":[16],"challenging":[18],"task":[19],"low":[21],"signal-to-noise":[22],"ratio":[23],"(SNR)":[24],"noisy":[25,78],"conditions.":[26],"Intuitively,":[27],"reducing":[28],"noise":[29],"will":[30],"improve":[31],"the":[32,65,74,106,110,125],"VAD.":[33],"Therefore,":[34],"this":[36],"study,":[37],"we":[38],"introduce":[39],"speech":[41,56,79,94],"enhancement":[42,57,95],"module":[43,58],"to":[44,61],"reduce":[45,62],"noise.":[46,63],"Specifically,":[47],"convolutional":[49,86],"recurrent":[50],"neural":[51,87],"network":[52,88],"(CRN)":[53],"based":[54,90],"encoder-decoder":[55],"trained":[60,102],"Then":[64],"low-dimensional":[66],"features":[67],"code":[68],"from":[69],"its":[70],"encoder":[71],"together":[72],"with":[73],"raw":[75],"spectrum":[76],"of":[77,109],"are":[80,99],"feed":[81],"into":[82],"deep":[84],"residual":[85],"(ResCNN)":[89],"VAD":[91,97],"module.":[92],"The":[93],"and":[96,101],"modules":[98],"connected":[100],"jointly.":[103],"To":[104],"balance":[105,117],"training":[107],"speed":[108],"two":[111],"modules,":[112],"an":[113],"empirical":[114],"dynamic":[115],"gradient":[116],"strategy":[118],"proposed.":[120],"Experimental":[121],"results":[122],"show":[123],"that":[124],"proposed":[126],"joint-training":[127],"method":[128],"has":[129],"obvious":[130],"advantages":[131],"generalization":[133],"ability.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}