{"id":"https://openalex.org/W2009833213","doi":"https://doi.org/10.1109/icics.2011.6174267","title":"An adaptive soft voice activity detector for automatic speech recognition system","display_name":"An adaptive soft voice activity detector for automatic speech recognition system","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W2009833213","doi":"https://doi.org/10.1109/icics.2011.6174267","mag":"2009833213"},"language":"en","primary_location":{"id":"doi:10.1109/icics.2011.6174267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icics.2011.6174267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 8th International Conference on Information, Communications &amp; Signal Processing","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/A5044434852","display_name":"Peng Dai","orcid":"https://orcid.org/0000-0002-3015-7485"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Peng Dai","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore","[School of Electrical and Electronic Engineering, Nanyang Technological University Singapore, Singapore]"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"[School of Electrical and Electronic Engineering, Nanyang Technological University Singapore, Singapore]","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111739626","display_name":"Ing Yann Soon","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ing Yann Soon","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore","[School of Electrical and Electronic Engineering, Nanyang Technological University Singapore, Singapore]"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"[School of Electrical and Electronic Engineering, Nanyang Technological University Singapore, Singapore]","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5044434852"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.9187,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.72832524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"75","issue":null,"first_page":"1","last_page":"5"},"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":0.9995999932289124,"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":0.9991999864578247,"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/voice-activity-detection","display_name":"Voice activity detection","score":0.8160243034362793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8116956949234009},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7427376508712769},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6529354453086853},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5705100893974304},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4953285753726959},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4539076089859009},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.41628211736679077},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3772258460521698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3576645851135254},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34837210178375244}],"concepts":[{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.8160243034362793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8116956949234009},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7427376508712769},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6529354453086853},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5705100893974304},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4953285753726959},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4539076089859009},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.41628211736679077},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3772258460521698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3576645851135254},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34837210178375244},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icics.2011.6174267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icics.2011.6174267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 8th International Conference on Information, Communications &amp; Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W1562951200","https://openalex.org/W2050091530","https://openalex.org/W2060895888","https://openalex.org/W2121973264","https://openalex.org/W2122972875","https://openalex.org/W2128653836","https://openalex.org/W2146324387","https://openalex.org/W2151484683","https://openalex.org/W2152131029","https://openalex.org/W2158336491","https://openalex.org/W2163839957","https://openalex.org/W2405735461","https://openalex.org/W3147539069","https://openalex.org/W6633699290"],"related_works":["https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2069501481","https://openalex.org/W1523214805","https://openalex.org/W4294771049","https://openalex.org/W2559040841","https://openalex.org/W2341426843","https://openalex.org/W4389247473","https://openalex.org/W2131711534"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,18,29,74],"novel":[4,30],"Adaptive":[5],"Voice":[6],"Activity":[7],"Detection":[8],"(VAD)":[9],"algorithm":[10,85,98],"is":[11,14,50],"proposed,":[12],"which":[13],"successfully":[15],"implemented":[16],"in":[17],"MFCC":[19],"based":[20],"speech":[21,34,42,49,62],"recognition":[22,63],"system.":[23],"The":[24],"proposed":[25,58,84,97],"adaptive":[26],"VAD":[27,59],"describes":[28],"scheme":[31],"of":[32,41,56],"detecting":[33],"presence/absence":[35],"by":[36],"tracking":[37],"the":[38,54,57,83,96],"higher":[39],"portion":[40],"power":[43],"spectrum.":[44],"Both":[45],"clean":[46],"and":[47],"noisy":[48],"used":[51],"to":[52,87,100],"show":[53,81,94],"effectiveness":[55],"algorithm.":[60],"Besides,":[61],"experiments":[64],"are":[65,70],"also":[66],"conducted.":[67],"Evaluation":[68],"tests":[69],"carried":[71],"out":[72],"using":[73],"standard":[75],"English":[76],"database,":[77],"AURORA2.":[78],"Experimental":[79,92],"results":[80,93],"that":[82,95],"manages":[86,99],"achieve":[88,101],"very":[89],"impressive":[90],"improvements.":[91,103],"significant":[102]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
