{"id":"https://openalex.org/W2907654220","doi":"https://doi.org/10.1109/sips.2018.8598422","title":"Multi-mode Study of Deep Learning Applications in Acoustic Signal Processing","display_name":"Multi-mode Study of Deep Learning Applications in Acoustic Signal Processing","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2907654220","doi":"https://doi.org/10.1109/sips.2018.8598422","mag":"2907654220"},"language":"en","primary_location":{"id":"doi:10.1109/sips.2018.8598422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips.2018.8598422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Workshop on Signal Processing Systems (SiPS)","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/A5003434623","display_name":"Sheng Guan","orcid":"https://orcid.org/0000-0003-0977-1787"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Guan","raw_affiliation_strings":["State Key Lab. of ASIC and System, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab. of ASIC and System, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002595006","display_name":"Weicheng He","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weicheng He","raw_affiliation_strings":["State Key Lab. of ASIC and System, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab. of ASIC and System, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100959368","display_name":"Wenjin Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjin Gu","raw_affiliation_strings":["State Key Lab. of ASIC and System, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab. of ASIC and System, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102064994","display_name":"Hou YuanZhao","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanzhao Hou","raw_affiliation_strings":["State Key Lab. of ASIC and System, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab. of ASIC and System, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101996379","display_name":"Yun Chen","orcid":"https://orcid.org/0000-0002-3736-9456"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Chen","raw_affiliation_strings":["State Key Lab. of ASIC and System, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab. of ASIC and System, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115590332","display_name":"Xiaoyang Zeng","orcid":"https://orcid.org/0000-0003-3986-137X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyang Zeng","raw_affiliation_strings":["State Key Lab. of ASIC and System, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab. of ASIC and System, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1663,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.49273284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"292","last_page":"295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8246892690658569},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.6195072531700134},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5707220435142517},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5652413368225098},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5518249273300171},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5310809016227722},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5187214016914368},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5047069787979126},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4881196916103363},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.47372379899024963},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.47318339347839355},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.46795713901519775},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43816107511520386},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35645192861557007},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.18835678696632385},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.1541053056716919},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.11153373122215271}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8246892690658569},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.6195072531700134},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5707220435142517},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5652413368225098},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5518249273300171},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5310809016227722},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5187214016914368},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5047069787979126},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4881196916103363},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.47372379899024963},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.47318339347839355},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.46795713901519775},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43816107511520386},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35645192861557007},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.18835678696632385},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.1541053056716919},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.11153373122215271},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sips.2018.8598422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips.2018.8598422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Workshop on Signal Processing Systems (SiPS)","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":27,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1563017489","https://openalex.org/W1970578576","https://openalex.org/W1984541135","https://openalex.org/W2086384421","https://openalex.org/W2124537004","https://openalex.org/W2136922672","https://openalex.org/W2147800946","https://openalex.org/W2509065397","https://openalex.org/W2528841789","https://openalex.org/W2542605056","https://openalex.org/W2566935005","https://openalex.org/W2591013610","https://openalex.org/W2604319603","https://openalex.org/W2735263571","https://openalex.org/W2763761345","https://openalex.org/W2775505379","https://openalex.org/W2797833340","https://openalex.org/W2963037989","https://openalex.org/W2963543871","https://openalex.org/W3098357269","https://openalex.org/W4297686742","https://openalex.org/W6741024066","https://openalex.org/W6744964450","https://openalex.org/W6747331233","https://openalex.org/W6750449942","https://openalex.org/W6766721818"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W3097613282","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W1975359510","https://openalex.org/W3004352674","https://openalex.org/W2088690926"],"abstract_inverted_index":{"This":[0],"proposed":[1],"an":[2,65],"intelligent":[3],"acoustic":[4,22],"signal":[5],"processing":[6,63],"system":[7,19,50],"based":[8],"on":[9],"deep":[10,15],"neural":[11],"networks":[12],"(DNNs).":[13],"Employing":[14],"learning":[16],"algorithms,":[17],"our":[18],"can":[20,60],"perform":[21],"scene":[23],"classification,":[24],"audio":[25,66],"tagging":[26],"and":[27,42,68],"(rare)":[28],"sound":[29],"event":[30],"detection,":[31],"achieving":[32],"a":[33],"high":[34],"performance":[35],"in":[36],"terms":[37],"of":[38,48,64],"accuracy,":[39],"error":[40],"rate":[41],"so":[43],"on.":[44],"An":[45],"attracting":[46],"feature":[47],"the":[49],"is":[51],"that":[52],"it":[53],"integrate":[54],"four":[55],"working":[56],"modes":[57],"together,":[58],"which":[59],"do":[61],"parallel":[62],"record":[67],"give":[69],"results":[70],"from":[71],"different":[72],"aspects.":[73]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
