{"id":"https://openalex.org/W2972940518","doi":"https://doi.org/10.21437/interspeech.2019-1579","title":"An End-to-End Audio Classification System Based on Raw Waveforms and Mix-Training Strategy","display_name":"An End-to-End Audio Classification System Based on Raw Waveforms and Mix-Training Strategy","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972940518","doi":"https://doi.org/10.21437/interspeech.2019-1579","mag":"2972940518"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1579","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/A5036550978","display_name":"Jiaxu Chen","orcid":"https://orcid.org/0000-0002-5570-6233"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiaxu Chen","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101751546","display_name":"Jing Hao","orcid":"https://orcid.org/0000-0002-2305-1201"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Hao","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437976","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0002-5624-2987"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636142","display_name":"Di Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Xie","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056516274","display_name":"Shicai Yang","orcid":"https://orcid.org/0000-0002-9260-1334"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shicai Yang","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085955762","display_name":"Shiliang Pu","orcid":"https://orcid.org/0000-0001-5269-7821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiliang Pu","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5036550978"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09555665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3644","last_page":"3648"},"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":0.9952999949455261,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9743000268936157,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8051384687423706},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8016998767852783},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6465185880661011},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5369851589202881},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5223197340965271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5024893283843994},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.49094679951667786},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4774080812931061},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.4268793761730194},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.42371535301208496},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.42198652029037476},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41299688816070557},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40658628940582275},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.18105962872505188},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09656119346618652},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0655030906200409}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8051384687423706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8016998767852783},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6465185880661011},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5369851589202881},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5223197340965271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5024893283843994},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.49094679951667786},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4774080812931061},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.4268793761730194},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.42371535301208496},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.42198652029037476},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41299688816070557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40658628940582275},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.18105962872505188},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09656119346618652},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0655030906200409},{"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-1579","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1972567154","https://openalex.org/W2031342017","https://openalex.org/W2194775991","https://openalex.org/W2342547278","https://openalex.org/W2526050071","https://openalex.org/W2529337537","https://openalex.org/W2570915410","https://openalex.org/W2593116425","https://openalex.org/W2593451766","https://openalex.org/W2765407302","https://openalex.org/W2768188490","https://openalex.org/W2775505379","https://openalex.org/W2791956393","https://openalex.org/W2804613703","https://openalex.org/W2889309940","https://openalex.org/W2962910554","https://openalex.org/W2963022469","https://openalex.org/W3027169863","https://openalex.org/W4293665662","https://openalex.org/W4297791000"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2110523656","https://openalex.org/W2521627374","https://openalex.org/W3172695526"],"abstract_inverted_index":{"Audio":[0,139],"classification":[1,40,136],"can":[2,87],"distinguish":[3],"different":[4],"kinds":[5],"of":[6,80,83,123,132],"sounds,":[7],"which":[8,52,86],"is":[9,30,104,142],"helpful":[10],"for":[11,70],"intelligent":[12],"applications":[13],"in":[14,26,57,95,106],"daily":[15],"life.However,":[16],"it":[17],"remains":[18],"a":[19,89,98,111],"challenging":[20],"task":[21],"since":[22],"the":[23,93,116,121,128,133,151],"sound":[24],"events":[25],"an":[27,37],"audio":[28,39,135],"clip":[29],"probably":[31],"multiple,":[32],"even":[33],"overlapping.This":[34],"paper":[35],"introduces":[36],"end-to-end":[38],"system":[41,137,149],"based":[42],"on":[43,138],"raw":[44,60,73],"waveforms":[45,61,74],"and":[46,66],"mix-training":[47,112],"strategy.Compared":[48],"to":[49,114],"human-designed":[50],"features":[51],"have":[53],"been":[54],"widely":[55],"used":[56],"existing":[58],"research,":[59],"contain":[62],"more":[63,68],"complete":[64],"information":[65,94],"are":[67],"appropriate":[69],"multi-label":[71],"classification.Taking":[72],"as":[75],"input,":[76],"our":[77,107,148],"network":[78],"consists":[79],"two":[81],"variants":[82],"ResNet":[84],"structure":[85,103],"learn":[88],"discriminative":[90],"representation.To":[91],"explore":[92],"intermediate":[96],"layers,":[97],"multi-level":[99,153],"prediction":[100],"with":[101],"attention":[102,154],"applied":[105],"model.Furthermore,":[108],"we":[109],"design":[110],"strategy":[113],"break":[115],"performance":[117],"limitation":[118],"caused":[119],"by":[120],"amount":[122],"training":[124,146],"data.Experiments":[125],"show":[126],"that":[127],"mean":[129],"average":[130],"precision":[131],"proposed":[134],"Set":[140],"dataset":[141],"37.2%.Without":[143],"using":[144],"extra":[145],"data,":[147],"exceeds":[150],"state-of-the-art":[152],"model.":[155]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}