{"id":"https://openalex.org/W3012546915","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023074","title":"Deep Neural Networks with Batch Speaker Normalization for Intoxicated Speech Detection","display_name":"Deep Neural Networks with Batch Speaker Normalization for Intoxicated Speech Detection","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3012546915","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023074","mag":"3012546915"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023074","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/A5100372965","display_name":"Weiqing Wang","orcid":"https://orcid.org/0000-0002-9578-819X"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weiqing Wang","raw_affiliation_strings":["Data Science Research Center, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079117782","display_name":"Haiwei Wu","orcid":"https://orcid.org/0000-0001-8807-0254"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiwei Wu","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Data Science Research Center, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100372965"],"corresponding_institution_ids":["https://openalex.org/I4210159968"],"apc_list":null,"apc_paid":null,"fwci":0.2894,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.69141847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1323","last_page":"1327"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"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":0.9980999827384949,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9484000205993652,"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/normalization","display_name":"Normalization (sociology)","score":0.8795541524887085},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7472816705703735},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6603524684906006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5930275321006775},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5872617959976196},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5659512877464294},{"id":"https://openalex.org/keywords/subnetwork","display_name":"Subnetwork","score":0.563742458820343},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5439711213111877},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.504018247127533},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.4618567228317261},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43830758333206177},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4342823028564453},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.42634493112564087},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0865827202796936}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8795541524887085},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7472816705703735},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6603524684906006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5930275321006775},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5872617959976196},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5659512877464294},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.563742458820343},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5439711213111877},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.504018247127533},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.4618567228317261},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43830758333206177},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4342823028564453},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.42634493112564087},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0865827202796936},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023074","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W44821376","https://openalex.org/W1524333225","https://openalex.org/W1533471977","https://openalex.org/W1970434625","https://openalex.org/W1976544739","https://openalex.org/W1999674789","https://openalex.org/W2007195631","https://openalex.org/W2008908123","https://openalex.org/W2031619410","https://openalex.org/W2039525862","https://openalex.org/W2058518981","https://openalex.org/W2060946996","https://openalex.org/W2066017813","https://openalex.org/W2071843190","https://openalex.org/W2085662862","https://openalex.org/W2090777335","https://openalex.org/W2096460743","https://openalex.org/W2101234009","https://openalex.org/W2144005487","https://openalex.org/W2176766250","https://openalex.org/W2194775991","https://openalex.org/W2265652568","https://openalex.org/W2296199791","https://openalex.org/W2726515241","https://openalex.org/W2740375526","https://openalex.org/W2963077989","https://openalex.org/W2963371159","https://openalex.org/W2972455439","https://openalex.org/W4230684441","https://openalex.org/W6631915201","https://openalex.org/W6639038027","https://openalex.org/W6675354045","https://openalex.org/W6681409903","https://openalex.org/W6693425903","https://openalex.org/W6697151493","https://openalex.org/W6741967235"],"related_works":["https://openalex.org/W4297841654","https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W4235705411","https://openalex.org/W1493012537","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Alcohol":[0],"intoxication":[1,51],"can":[2,156],"affect":[3],"people":[4],"both":[5,161],"physically":[6],"and":[7,9,40,85,137,146,165],"psychologically,":[8],"one's":[10],"speech":[11,23],"will":[12],"also":[13,115],"become":[14],"different.":[15],"However,":[16],"detecting":[17],"the":[18,22,34,43,46,50,100,106,111,121,125,158,162,166],"intoxicated":[19],"state":[20],"from":[21],"is":[24],"a":[25,57,69,80,86],"challenging":[26],"task.":[27,53,63],"In":[28],"this":[29,62],"paper,":[30],"we":[31,55,94,104],"first":[32],"implement":[33],"baseline":[35,126,135,163],"model":[36,60,65,136,143,164],"with":[37,73],"ComParE":[38],"feature":[39,102],"then":[41],"explore":[42],"influence":[44],"of":[45,78,88,160],"speaker":[47,97,122,132,154],"information":[48],"on":[49,99,134,140],"detection":[52],"Besides,":[54],"apply":[56],"ResNet18":[58,141],"based":[59,142],"to":[61,109,124],"The":[64,150],"contains":[66],"three":[67],"parts:":[68],"representation":[70],"learning":[71],"subnetwork":[72],"Deep":[74],"Residual":[75],"Neural":[76],"Network(ResNet)":[77],"18-layer,":[79],"global":[81],"average":[82],"pooling(GAP)":[83],"layer":[84],"classifier":[87],"2":[89],"fully":[90],"connected":[91],"layers.":[92],"Since":[93],"cannot":[95],"perform":[96],"z-normalization":[98,108,139],"variant-length":[101],"input,":[103],"employ":[105],"batch":[107,138],"train":[110],"proposed":[112,167],"model.":[113,168],"It":[114],"achieves":[116],"similar":[117],"improvement":[118,148],"like":[119],"applying":[120],"normalization":[123,133,155],"method.":[127],"Experimental":[128],"results":[129,151],"show":[130,152],"that":[131,153],"provides":[144],"4.9%":[145],"3.8%":[147],"respectively.":[149],"improve":[157],"performance":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}