{"id":"https://openalex.org/W4392904462","doi":"https://doi.org/10.1109/icassp48485.2024.10448117","title":"ByteHum: Fast and Accurate Query-by-Humming in the Wild","display_name":"ByteHum: Fast and Accurate Query-by-Humming in the Wild","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904462","doi":"https://doi.org/10.1109/icassp48485.2024.10448117"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5091528537","display_name":"Xingjian Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xingjian Du","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101813286","display_name":"Pei Zou","orcid":"https://orcid.org/0000-0001-6116-5878"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei Zou","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100335524","display_name":"Ming-Yu Liu","orcid":"https://orcid.org/0000-0002-2239-8975"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingyu Liu","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094178998","display_name":"Xia Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia Liang","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111148992","display_name":"Minghang Chu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minghang Chu","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100934338","display_name":"Bilei Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bilei Zhu","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5091528537"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3735,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49408363,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1111","last_page":"1115"},"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":0.9916999936103821,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8720258474349976},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6511338949203491},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.5552911162376404},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5168881416320801},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46374639868736267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4530557692050934},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44461870193481445},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4224976599216461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8720258474349976},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6511338949203491},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.5552911162376404},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5168881416320801},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46374639868736267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4530557692050934},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44461870193481445},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4224976599216461},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":20,"referenced_works":["https://openalex.org/W96254548","https://openalex.org/W188196595","https://openalex.org/W1493535305","https://openalex.org/W2027518030","https://openalex.org/W2099001086","https://openalex.org/W2101722322","https://openalex.org/W2142669986","https://openalex.org/W2748574178","https://openalex.org/W2786429113","https://openalex.org/W2896276533","https://openalex.org/W3161928252","https://openalex.org/W3183810078","https://openalex.org/W4224920338","https://openalex.org/W4308086144","https://openalex.org/W4312947874","https://openalex.org/W4372266723","https://openalex.org/W4385822341","https://openalex.org/W6603909643","https://openalex.org/W6607673643","https://openalex.org/W6639480849"],"related_works":["https://openalex.org/W2114097550","https://openalex.org/W4385352507","https://openalex.org/W2918559346","https://openalex.org/W84309476","https://openalex.org/W4286904253","https://openalex.org/W2386245264","https://openalex.org/W4389912005","https://openalex.org/W4391021514","https://openalex.org/W2388033618","https://openalex.org/W105599799"],"abstract_inverted_index":{"Query":[0],"by":[1],"Humming":[2],"(QBH)":[3],"is":[4,49],"a":[5,41,69,81],"practically":[6],"meaningful":[7],"task,":[8],"while":[9],"most":[10],"existing":[11,136,148],"methods":[12],"struggle":[13],"to":[14,16,20,73,104,118],"scale":[15],"real-life":[17],"applications":[18],"due":[19],"the":[21,26,29,38,62,92,97,106,114,128],"complex":[22],"preprocessing":[23],"for":[24,64,87,134],"building":[25],"database":[27],"and":[28,43,79,155,160],"limited":[30],"search":[31],"speed.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36,130],"propose":[37],"ByteHum":[39,67,145],"system,":[40],"fast":[42],"efficient":[44],"humming":[45],"retrieval":[46],"system":[47],"which":[48],"capable":[50],"of":[51,91,99,108,153],"searching":[52],"against":[53],"large-scale":[54],"databases":[55,126],"built":[56],"on":[57,113,123],"raw":[58,77],"song":[59,84],"audios":[60],"without":[61],"need":[63],"extensive":[65],"preprocessing.":[66],"employs":[68],"convolutional":[70],"neural":[71],"network":[72],"extract":[74],"features":[75],"from":[76],"audio,":[78],"utilizes":[80],"source-separated":[82],"cover":[83],"identification":[85],"dataset":[86],"weakly":[88,110],"supervised":[89,111],"training":[90],"feature":[93],"extractor.":[94],"We":[95],"explore":[96],"use":[98],"unsupervised":[100],"domain":[101],"adaptation":[102],"techniques":[103],"enhance":[105],"performance":[107,122],"our":[109],"model":[112],"QBH":[115,120,137,149],"task.":[116],"Furthermore,":[117],"evaluate":[119],"systems\u2019":[121],"non-manually":[124],"processed":[125],"in":[127,151],"wild,":[129],"annotate":[131],"original":[132],"recordings":[133],"three":[135],"benchmark":[138],"sets.":[139],"Our":[140],"experimental":[141],"results":[142],"demonstrate":[143],"that":[144],"significantly":[146],"outperforms":[147],"systems":[150],"terms":[152],"speed":[154],"accuracy":[156],"under":[157],"both":[158],"classical":[159],"unconstrained":[161],"settings.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}