{"id":"https://openalex.org/W2990743895","doi":"https://doi.org/10.1145/3366194.3366219","title":"Sub-voice Detection and Recognition based on Hybrid Audio Segmentation and Deep Learning","display_name":"Sub-voice Detection and Recognition based on Hybrid Audio Segmentation and Deep Learning","publication_year":2019,"publication_date":"2019-09-20","ids":{"openalex":"https://openalex.org/W2990743895","doi":"https://doi.org/10.1145/3366194.3366219","mag":"2990743895"},"language":"en","primary_location":{"id":"doi:10.1145/3366194.3366219","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3366194.3366219","pdf_url":null,"source":{"id":"https://openalex.org/S4306523677","display_name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","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/A5100299112","display_name":"Xiaolei Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156464","display_name":"Anhui Xinhua University","ror":"https://ror.org/053d7x641","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210156464"]},{"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":true,"raw_author_name":"Xiaolei Zhao","raw_affiliation_strings":["School of Information Science, Xinhua College of Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science, Xinhua College of Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I4210156464","https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101974371","display_name":"Chenyin Wang","orcid":"https://orcid.org/0000-0001-8853-4805"},"institutions":[{"id":"https://openalex.org/I4210156464","display_name":"Anhui Xinhua University","ror":"https://ror.org/053d7x641","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210156464"]},{"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":"Chenyin Wang","raw_affiliation_strings":["School of Information Science, Xinhua College of Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science, Xinhua College of Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I4210156464","https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103712994","display_name":"Xibin Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092267","display_name":"Guangdong Industry Technical College","ror":"https://ror.org/00dre6z66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092267"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xibin Xu","raw_affiliation_strings":["Guangdong Engineering Vocational and Technical College, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Engineering Vocational and Technical College, Guangzhou, China","institution_ids":["https://openalex.org/I4210092267"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100299112"],"corresponding_institution_ids":["https://openalex.org/I157773358","https://openalex.org/I4210156464"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15235457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"41","issue":null,"first_page":"143","last_page":"147"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9908000230789185,"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":0.9908000230789185,"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":0.9868999719619751,"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":0.9750000238418579,"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":0.7709459066390991},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6978502869606018},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.690714955329895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6400768756866455},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5662147998809814},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5457373261451721},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.525931179523468},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.515898585319519},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5047646760940552},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5027821063995361},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.49101853370666504},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4693413972854614},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.22614344954490662}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7709459066390991},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6978502869606018},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.690714955329895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6400768756866455},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5662147998809814},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5457373261451721},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.525931179523468},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.515898585319519},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5047646760940552},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5027821063995361},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.49101853370666504},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4693413972854614},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.22614344954490662},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3366194.3366219","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3366194.3366219","pdf_url":null,"source":{"id":"https://openalex.org/S4306523677","display_name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1616262590","https://openalex.org/W1964184389","https://openalex.org/W2017154415","https://openalex.org/W2044591814","https://openalex.org/W2052454896","https://openalex.org/W2074996852","https://openalex.org/W2331996894","https://openalex.org/W2557092978","https://openalex.org/W2621829342","https://openalex.org/W2729124190","https://openalex.org/W2769669558","https://openalex.org/W2895625244","https://openalex.org/W2920584997","https://openalex.org/W3102431071"],"related_works":["https://openalex.org/W4214896311","https://openalex.org/W2184242386","https://openalex.org/W2325729322","https://openalex.org/W1923358586","https://openalex.org/W3006475563","https://openalex.org/W1560125148","https://openalex.org/W3015707499","https://openalex.org/W2049462786","https://openalex.org/W4287868249","https://openalex.org/W2326728821"],"abstract_inverted_index":{"Sub-voice":[0],"(crying,":[1],"laughter,":[2],"sigh,":[3],"etc.)":[4],"carries":[5],"a":[6,16],"large":[7],"amount":[8],"of":[9,12,33,38,107],"effective":[10],"information":[11],"speakers,":[13],"and":[14,26,31,40,51,64,80,117],"has":[15],"huge":[17],"auxiliary":[18],"role":[19],"in":[20],"emotion":[21],"recognition,":[22,24],"behavior":[23],"physiological":[25],"psychology":[27],"research.":[28],"Correct":[29],"detection":[30,50,105,110],"recognition":[32,120,131],"subvoice":[34],"is":[35,44,67,94,112,122],"the":[36,84,104,108,118,126],"premise":[37],"research":[39],"application.":[41],"The":[42,54,91,99],"method":[43,111,121],"divided":[45],"into":[46,83],"two":[47],"phases:":[48],"sub-voice":[49,52,71],"recognition.":[53],"high-efficiency":[55],"hybrid":[56],"audio":[57],"segmentation":[58],"algorithm":[59],"based":[60],"on":[61],"likelihood":[62],"ratio":[63],"model":[65,93],"pre-judgment":[66],"used":[68,96],"to":[69,87],"realize":[70],"detection.":[72],"After":[73],"detecting":[74],"sub-voice,":[75],"we":[76],"extract":[77,89],"grayscale":[78],"spectrograms,":[79],"input":[81],"them":[82],"PCANET":[85],"network":[86],"automatically":[88],"features.":[90],"SVM":[92],"then":[95],"for":[97],"identification.":[98],"experimental":[100],"results":[101],"show":[102],"that":[103],"accuracy":[106],"proposed":[109,119],"as":[113,115],"high":[114],"94.2%,":[116],"7.7%":[123],"higher":[124],"than":[125],"traditional":[127],"artificial":[128],"statistical":[129],"feature":[130],"method.":[132]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}