{"id":"https://openalex.org/W2785459660","doi":"https://doi.org/10.1109/apsipa.2017.8282048","title":"Robust voice activity detection based on LSTM recurrent neural networks and modulation spectrum","display_name":"Robust voice activity detection based on LSTM recurrent neural networks and modulation spectrum","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2785459660","doi":"https://doi.org/10.1109/apsipa.2017.8282048","mag":"2785459660"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282048","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5083133506","display_name":"Phuttapong Sertsi","orcid":null},"institutions":[{"id":"https://openalex.org/I1332092204","display_name":"National Science and Technology Development Agency","ror":"https://ror.org/04vy95b61","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204"]},{"id":"https://openalex.org/I14316845","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}],"countries":["TH"],"is_corresponding":true,"raw_author_name":"Phuttapong Sertsi","raw_affiliation_strings":["National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), 112 Pahonyothin Road, Pathumthani, 12120, Thailand"],"affiliations":[{"raw_affiliation_string":"National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]},{"raw_affiliation_string":"National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), 112 Pahonyothin Road, Pathumthani, 12120, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031542922","display_name":"Surasak Boonkla","orcid":"https://orcid.org/0000-0002-8746-9615"},"institutions":[{"id":"https://openalex.org/I1332092204","display_name":"National Science and Technology Development Agency","ror":"https://ror.org/04vy95b61","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204"]},{"id":"https://openalex.org/I14316845","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Surasak Boonkla","raw_affiliation_strings":["National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), 112 Pahonyothin Road, Pathumthani, 12120, Thailand"],"affiliations":[{"raw_affiliation_string":"National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]},{"raw_affiliation_string":"National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), 112 Pahonyothin Road, Pathumthani, 12120, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002206098","display_name":"Vataya Chunwijitra","orcid":null},"institutions":[{"id":"https://openalex.org/I1332092204","display_name":"National Science and Technology Development Agency","ror":"https://ror.org/04vy95b61","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204"]},{"id":"https://openalex.org/I14316845","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Vataya Chunwijitra","raw_affiliation_strings":["National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), 112 Pahonyothin Road, Pathumthani, 12120, Thailand"],"affiliations":[{"raw_affiliation_string":"National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]},{"raw_affiliation_string":"National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), 112 Pahonyothin Road, Pathumthani, 12120, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025925774","display_name":"Nattapong Kurpukdee","orcid":null},"institutions":[{"id":"https://openalex.org/I1332092204","display_name":"National Science and Technology Development Agency","ror":"https://ror.org/04vy95b61","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204"]},{"id":"https://openalex.org/I14316845","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Nattapong Kurpukdee","raw_affiliation_strings":["National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), 112 Pahonyothin Road, Pathumthani, 12120, Thailand"],"affiliations":[{"raw_affiliation_string":"National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]},{"raw_affiliation_string":"National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), 112 Pahonyothin Road, Pathumthani, 12120, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065708730","display_name":"Chai Wutiwiwatchai","orcid":null},"institutions":[{"id":"https://openalex.org/I1332092204","display_name":"National Science and Technology Development Agency","ror":"https://ror.org/04vy95b61","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204"]},{"id":"https://openalex.org/I14316845","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Chai Wutiwiwatchai","raw_affiliation_strings":["National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), 112 Pahonyothin Road, Pathumthani, 12120, Thailand"],"affiliations":[{"raw_affiliation_string":"National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]},{"raw_affiliation_string":"National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), 112 Pahonyothin Road, Pathumthani, 12120, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5083133506"],"corresponding_institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"],"apc_list":null,"apc_paid":null,"fwci":1.8492,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.87428414,"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":"342","last_page":"346"},"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":0.9994000196456909,"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/robustness","display_name":"Robustness (evolution)","score":0.8459262847900391},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7985376119613647},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.789536714553833},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7128736972808838},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5193684697151184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47455888986587524},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.47271960973739624},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.46327683329582214},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4604857861995697},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46004512906074524},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4367560148239136},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4175513982772827},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1981920599937439},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07677781581878662}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8459262847900391},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7985376119613647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.789536714553833},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7128736972808838},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5193684697151184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47455888986587524},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.47271960973739624},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.46327683329582214},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4604857861995697},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46004512906074524},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4367560148239136},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4175513982772827},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1981920599937439},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07677781581878662},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2017.8282048","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W296042737","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1563939609","https://openalex.org/W1997193689","https://openalex.org/W1999454387","https://openalex.org/W2032362923","https://openalex.org/W2129120544","https://openalex.org/W2281740710","https://openalex.org/W2408468399","https://openalex.org/W6631190155","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2373767407","https://openalex.org/W3110551121","https://openalex.org/W2131486661","https://openalex.org/W4252682934","https://openalex.org/W2089240210","https://openalex.org/W2120771489","https://openalex.org/W642007152","https://openalex.org/W4200596008"],"abstract_inverted_index":{"Voice":[0],"activity":[1],"detection":[2],"(VAD)":[3],"used":[4,43],"for":[5,79],"classifying":[6,50],"speech/non-speech":[7],"sections":[8],"of":[9,82,92],"a":[10,76],"speech":[11,45,51,64],"signal":[12],"still":[13],"suffers":[14],"from":[15],"noisy":[16],"environments.":[17],"In":[18,72],"this":[19],"paper,":[20],"we":[21,74],"cooperate":[22],"the":[23,28,38,70,80,83,90,94,109],"modulation":[24],"spectrum":[25],"(MS)":[26],"and":[27,49,52,103],"long":[29],"short-term":[30],"memory":[31],"recurrent":[32],"neural":[33],"network":[34],"(LSTM)":[35],"to":[36,68],"improve":[37],"robustness.":[39,71],"The":[40,55,86],"baseline":[41,110],"LSTM":[42],"conventional":[44],"features":[46],"in":[47,66],"training":[48],"non-speech":[53],"sections.":[54],"proposed":[56,95],"VAD":[57],"system":[58],"by":[59],"using":[60,93],"MS":[61,84],"as":[62],"another":[63],"feature":[65],"order":[67],"increase":[69],"addition,":[73],"propose":[75],"new":[77],"approach":[78],"computation":[81],"feature.":[85],"results":[87],"showed":[88],"that":[89],"accuracy":[91],"method":[96],"can":[97],"be":[98],"improved":[99],"under":[100],"both":[101],"seen":[102],"unseen":[104],"noise":[105],"conditions":[106],"compared":[107],"with":[108],"technique.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3}],"updated_date":"2026-02-02T03:55:41.653505","created_date":"2025-10-10T00:00:00"}
