{"id":"https://openalex.org/W4415540026","doi":"https://doi.org/10.1145/3746027.3758298","title":"DogSpeak: A Canine Vocalization Classification Dataset","display_name":"DogSpeak: A Canine Vocalization Classification Dataset","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540026","doi":"https://doi.org/10.1145/3746027.3758298"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758298","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758298","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3758298","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119204534","display_name":"Hridayesh Lekhak","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hridayesh Lekhak","raw_affiliation_strings":["The University of Texas at Arlington, Arlington, Texas, USA"],"raw_orcid":"https://orcid.org/0009-0001-7256-7503","affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington, Arlington, Texas, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049450075","display_name":"Sinong Wang","orcid":"https://orcid.org/0009-0008-5329-9620"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Theron S. Wang","raw_affiliation_strings":["The University of Texas at Arlington, Arlington, Texas, USA"],"raw_orcid":"https://orcid.org/0009-0008-5329-9620","affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington, Arlington, Texas, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021381826","display_name":"Tuan M. Dang","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tuan M. Dang","raw_affiliation_strings":["The University of Texas at Arlington, Arlington, Texas, USA"],"raw_orcid":"https://orcid.org/0009-0004-0686-5184","affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington, Arlington, Texas, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101906756","display_name":"Kenny Q. Zhu","orcid":"https://orcid.org/0000-0003-3782-3230"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenny Q. Zhu","raw_affiliation_strings":["The University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-3782-3230","affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13369","last_page":"13375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13289","display_name":"Infant Health and Development","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T13289","display_name":"Infant Health and Development","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9983000159263611,"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/T11214","display_name":"Human-Animal Interaction Studies","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.60589998960495},{"id":"https://openalex.org/keywords/bioacoustics","display_name":"Bioacoustics","score":0.5202999711036682},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.519599974155426},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.46389999985694885},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.3540000021457672},{"id":"https://openalex.org/keywords/animal-communication","display_name":"Animal communication","score":0.30970001220703125}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.60589998960495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5529999732971191},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.5202999711036682},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.519599974155426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49559998512268066},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.46389999985694885},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3303999900817871},{"id":"https://openalex.org/C59726852","wikidata":"https://www.wikidata.org/wiki/Q1434121","display_name":"Animal communication","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30550000071525574},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28870001435279846},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C2992428333","wikidata":"https://www.wikidata.org/wiki/Q11461","display_name":"Sound production","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2533000111579895},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C2983406839","wikidata":"https://www.wikidata.org/wiki/Q921513","display_name":"Social behaviour","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3758298","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758298","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3758298","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758298","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6851658176","display_name":"REU Site: Animal Language Processing and Understanding","funder_award_id":"2349713","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2038166844","https://openalex.org/W2085662862","https://openalex.org/W2098531430","https://openalex.org/W2148154194","https://openalex.org/W2156248415","https://openalex.org/W2191779130","https://openalex.org/W2239141610","https://openalex.org/W2295598076","https://openalex.org/W2300894760","https://openalex.org/W2610298341","https://openalex.org/W2804973920","https://openalex.org/W2889749440","https://openalex.org/W2967542766","https://openalex.org/W3110727878","https://openalex.org/W3206438263","https://openalex.org/W4308877100","https://openalex.org/W4385567057","https://openalex.org/W4390939530","https://openalex.org/W4394989927","https://openalex.org/W4404780865","https://openalex.org/W4412945486","https://openalex.org/W4415433269"],"related_works":[],"abstract_inverted_index":{"Progress":[0],"in":[1],"understanding":[2],"real-world":[3,73],"canine":[4],"vocal":[5],"communication":[6],"is":[7],"constrained":[8],"by":[9],"datasets":[10],"lacking":[11],"scale":[12],"and":[13,44,68,76,85],"'in-the-wild'":[14],"diversity.":[15],"We":[16],"introduce":[17],"DogSpeak,":[18,47],"a":[19],"large-scale":[20],"public":[21],"dataset":[22],"of":[23,49,52],"77,202":[24],"Barkseqs":[25],"(33.162":[26],"hours)":[27],"from":[28,35],"156":[29],"dogs":[30],"(5":[31],"breeds),":[32],"uniquely":[33],"sourced":[34],"online":[36],"social":[37],"media":[38],"with":[39],"accurate":[40],"dog":[41,63],"ID,":[42],"sex,":[43],"breed":[45],"labels.":[46],"one":[48],"the":[50],"largest":[51],"its":[53,66,71],"kind,":[54],"addresses":[55],"prior":[56],"limitations.":[57],"Benchmark":[58],"tasks":[59],"(sex,":[60],"breed,":[61],"individual":[62],"recognition)":[64],"demonstrate":[65],"utility":[67],"highlight":[69],"how":[70],"inherent":[72],"challenges":[74],"necessitate":[75],"foster":[77],"research":[78],"into":[79],"more":[80],"robust":[81],"bioacoustic":[82],"models,":[83],"preprocessing,":[84],"feature":[86],"representation.":[87]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}
