{"id":"https://openalex.org/W7148570883","doi":"https://doi.org/10.1109/asru65441.2025.11434811","title":"Learning Marmoset Vocal Patterns with a Masked Autoencoder for Robust Call Segmentation, Classification, and Caller Identification","display_name":"Learning Marmoset Vocal Patterns with a Masked Autoencoder for Robust Call Segmentation, Classification, and Caller Identification","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148570883","doi":"https://doi.org/10.1109/asru65441.2025.11434811"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132786300","display_name":"Bin Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Bin Wu","raw_affiliation_strings":["RIKEN Center for Advanced Intelligence Project (AIP),Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project (AIP),Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["RIKEN Center for Advanced Intelligence Project (AIP),Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project (AIP),Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["RIKEN Center for Advanced Intelligence Project (AIP),Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project (AIP),Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["RIKEN Center for Advanced Intelligence Project (AIP),Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project (AIP),Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5132786300"],"corresponding_institution_ids":["https://openalex.org/I4210126580"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7508089,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.6328999996185303,"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":0.6328999996185303,"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":0.11739999800920486,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0778999999165535,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/autoencoder","display_name":"Autoencoder","score":0.70169997215271},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5914999842643738},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.482699990272522},{"id":"https://openalex.org/keywords/marmoset","display_name":"Marmoset","score":0.4296000003814697},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3027999997138977}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.70169997215271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6340000033378601},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.600600004196167},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5914999842643738},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.482699990272522},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4799000024795532},{"id":"https://openalex.org/C2776453536","wikidata":"https://www.wikidata.org/wiki/Q19829485","display_name":"Marmoset","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25760000944137573},{"id":"https://openalex.org/C159693508","wikidata":"https://www.wikidata.org/wiki/Q3301075","display_name":"Phonocardiogram","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335125","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1979064513","https://openalex.org/W1984508901","https://openalex.org/W2010352021","https://openalex.org/W2014745897","https://openalex.org/W2019887455","https://openalex.org/W2164889453","https://openalex.org/W2165275111","https://openalex.org/W2516168555","https://openalex.org/W2522347965","https://openalex.org/W2792354851","https://openalex.org/W2885248663","https://openalex.org/W2894955409","https://openalex.org/W3016361809","https://openalex.org/W4313156423","https://openalex.org/W4385245566","https://openalex.org/W4385823287"],"related_works":[],"abstract_inverted_index":{"The":[0,94],"marmoset,":[1],"a":[2,7],"highly":[3,22],"vocal":[4,114],"primate,":[5],"is":[6],"key":[8],"model":[9,111],"for":[10,59],"studying":[11],"social-communicative":[12],"behavior.":[13],"Unlike":[14],"human":[15],"speech,":[16],"marmoset":[17,31,92],"vocalizations":[18],"are":[19],"less":[20],"structured,":[21],"variable,":[23],"and":[24,38,66,98],"recorded":[25],"in":[26],"noisy,":[27],"low-resource":[28,112],"conditions.":[29],"Learning":[30],"communication":[32],"requires":[33],"joint":[34],"call":[35],"segmentation,":[36],"classification,":[37],"caller":[39],"identification-challenging":[40],"domain":[41],"tasks.":[42],"Previous":[43],"CNNs":[44],"handle":[45],"local":[46],"patterns":[47],"but":[48],"struggle":[49],"with":[50,79],"long-range":[51],"temporal":[52],"structure.":[53],"We":[54],"applied":[55],"Transformers":[56,63,78,103],"using":[57],"self-attention":[58],"global":[60],"dependencies.":[61],"However,":[62],"show":[64,101],"overfitting":[65],"instability":[67],"on":[68],"small,":[69],"noisy":[70],"annotated":[71],"datasets.":[72],"To":[73],"address":[74],"this,":[75],"we":[76],"pretrain":[77],"MAE-a":[80],"self-supervised":[81,108],"method":[82],"reconstructing":[83],"masked":[84],"segments":[85],"from":[86],"hundreds":[87],"of":[88,90],"hours":[89],"unannotated":[91],"recordings.":[93],"pretraining":[95],"improved":[96],"stability":[97],"generalization.":[99],"Results":[100],"MAE-pretrained":[102],"outperform":[104],"CNNs,":[105],"demonstrating":[106],"modern":[107],"architectures":[109],"effectively":[110],"non-human":[113],"communication.":[115]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-04-03T00:00:00"}