{"id":"https://openalex.org/W2911679849","doi":"https://doi.org/10.1109/icassp.2019.8682940","title":"CONV-codes: Audio Hashing for Bird Species Classification","display_name":"CONV-codes: Audio Hashing for Bird Species Classification","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2911679849","doi":"https://doi.org/10.1109/icassp.2019.8682940","mag":"2911679849"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5101642643","display_name":"Anshul Thakur","orcid":"https://orcid.org/0000-0002-2859-0634"},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Anshul Thakur","raw_affiliation_strings":["School of Computing and Electrical Engineering, IIT, Mandi, India"],"affiliations":[{"raw_affiliation_string":"School of Computing and Electrical Engineering, IIT, Mandi, India","institution_ids":["https://openalex.org/I9579091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783272","display_name":"Pulkit Sharma","orcid":"https://orcid.org/0000-0001-7870-7098"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pulkit Sharma","raw_affiliation_strings":["Computational Health Informatics Lab, University of Oxford, UK"],"affiliations":[{"raw_affiliation_string":"Computational Health Informatics Lab, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075520691","display_name":"Vinayak Abrol","orcid":"https://orcid.org/0000-0001-8149-8151"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Vinayak Abrol","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078300199","display_name":"P.K. Rajan","orcid":"https://orcid.org/0000-0002-9178-3885"},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Padmanabhan Rajan","raw_affiliation_strings":["School of Computing and Electrical Engineering, IIT, Mandi, India"],"affiliations":[{"raw_affiliation_string":"School of Computing and Electrical Engineering, IIT, Mandi, India","institution_ids":["https://openalex.org/I9579091"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101642643"],"corresponding_institution_ids":["https://openalex.org/I9579091"],"apc_list":null,"apc_paid":null,"fwci":0.3992,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.58333333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"8241","last_page":"8245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9943000078201294,"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/T10487","display_name":"Plant and animal studies","score":0.9161999821662903,"subfield":{"id":"https://openalex.org/subfields/1105","display_name":"Ecology, Evolution, Behavior and Systematics"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.7162976861000061},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.6502638459205627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6490172147750854},{"id":"https://openalex.org/keywords/double-hashing","display_name":"Double hashing","score":0.5494524836540222},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.5384976267814636},{"id":"https://openalex.org/keywords/dynamic-perfect-hashing","display_name":"Dynamic perfect hashing","score":0.4627402424812317},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.45400571823120117},{"id":"https://openalex.org/keywords/universal-hashing","display_name":"Universal hashing","score":0.4493579566478729},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4337722659111023},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.42236411571502686},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41730326414108276},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3292657732963562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28802746534347534}],"concepts":[{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7162976861000061},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.6502638459205627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6490172147750854},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.5494524836540222},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.5384976267814636},{"id":"https://openalex.org/C122907437","wikidata":"https://www.wikidata.org/wiki/Q5318999","display_name":"Dynamic perfect hashing","level":5,"score":0.4627402424812317},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.45400571823120117},{"id":"https://openalex.org/C116058348","wikidata":"https://www.wikidata.org/wiki/Q846912","display_name":"Universal hashing","level":5,"score":0.4493579566478729},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4337722659111023},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42236411571502686},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41730326414108276},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3292657732963562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28802746534347534},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.6899999976158142,"display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1537946535","https://openalex.org/W1565377632","https://openalex.org/W1993284846","https://openalex.org/W2012795698","https://openalex.org/W2069943693","https://openalex.org/W2076694837","https://openalex.org/W2106706131","https://openalex.org/W2111339618","https://openalex.org/W2117863804","https://openalex.org/W2127135195","https://openalex.org/W2132069633","https://openalex.org/W2149241068","https://openalex.org/W2150521923","https://openalex.org/W2156822626","https://openalex.org/W2585877841","https://openalex.org/W2613376785","https://openalex.org/W2767010978","https://openalex.org/W2773491457","https://openalex.org/W2891247746","https://openalex.org/W2963881378","https://openalex.org/W4205774955","https://openalex.org/W4300601563","https://openalex.org/W6648522431","https://openalex.org/W6676630944","https://openalex.org/W6679663036"],"related_works":["https://openalex.org/W2044784665","https://openalex.org/W2000284985","https://openalex.org/W1870428314","https://openalex.org/W2086731314","https://openalex.org/W2158169729","https://openalex.org/W4212830455","https://openalex.org/W2088296667","https://openalex.org/W2111153468","https://openalex.org/W4385382899","https://openalex.org/W2054549325"],"abstract_inverted_index":{"We":[0],"propose":[1,150],"a":[2,20,29,107,123,151],"supervised,":[3],"convex":[4,33],"representation":[5],"based":[6,142],"audio":[7,179],"hashing":[8],"framework":[9,16,121,156],"for":[10],"bird":[11,30,124,173,184],"species":[12,90,103,174],"classification.":[13,162],"The":[14,52,163],"proposed":[15,120,155],"utilizes":[17],"archetypal":[18],"analysis,":[19],"matrix":[21],"factorization":[22],"technique,":[23],"to":[24,44,88,100,106],"obtain":[25,45],"convex-sparse":[26],"representations":[27,34],"of":[28,153,165,181],"vocalization.":[31],"These":[32],"are":[35,59,86,169],"hashed":[36],"using":[37,61,77],"Bloom":[38],"filters":[39],"with":[40,65,114,171],"non-cryptographic":[41],"hash":[42,73,84,96],"functions":[43],"compact":[46],"binary":[47],"codes,":[48],"designated":[49],"as":[50,68,81],"conv-codes.":[51],"conv-codes":[53],"extracted":[54],"from":[55,140],"the":[56,69,78,89,95,102,115,119,127,154,178],"training":[57],"examples":[58],"clustered":[60],"class-specific":[62],"k-medoids":[63],"clustering":[64],"Jaccard":[66],"coefficient":[67],"similarity":[70,113],"metric.":[71],"A":[72],"table":[74,97],"is":[75,98],"populated":[76],"cluster":[79,108],"centers":[80],"keys":[82],"while":[83],"values/slots":[85],"pointers":[87],"identification":[91],"information.":[92],"During":[93],"testing,":[94],"searched":[99],"find":[101],"information":[104],"corresponding":[105],"center":[109],"that":[110,157],"exhibits":[111],"maximum":[112],"test":[116],"conv-code.":[117],"Hence,":[118],"classifies":[122],"vocalization":[125],"in":[126],"conv-code":[128],"space":[129],"and":[130,145,160],"requires":[131],"no":[132],"explicit":[133],"classifier":[134],"or":[135],"reconstruction":[136],"error":[137],"calculations.":[138],"Apart":[139],"that,":[141],"on":[143,177],"min-hash":[144],"direct":[146],"addressing,":[147],"we":[148],"also":[149],"variant":[152],"provides":[158],"faster":[159],"effective":[161],"performances":[164],"both":[166],"these":[167],"frameworks":[168,176],"compared":[170],"existing":[172],"classification":[175],"recordings":[180],"50":[182],"different":[183],"species.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}