{"id":"https://openalex.org/W4416183378","doi":"https://doi.org/10.1109/sibgrapi67909.2025.11223394","title":"Isolating Vocalizations Beats Denoising: Spectrogram Granularity and Preprocessing in Ecoacoustic Classification","display_name":"Isolating Vocalizations Beats Denoising: Spectrogram Granularity and Preprocessing in Ecoacoustic Classification","publication_year":2025,"publication_date":"2025-09-30","ids":{"openalex":"https://openalex.org/W4416183378","doi":"https://doi.org/10.1109/sibgrapi67909.2025.11223394"},"language":null,"primary_location":{"id":"doi:10.1109/sibgrapi67909.2025.11223394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sibgrapi67909.2025.11223394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 38th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","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/A5109644474","display_name":"Gustavo L. Lopes","orcid":null},"institutions":[{"id":"https://openalex.org/I2799978770","display_name":"X-Fab (Germany)","ror":"https://ror.org/030bh9196","country_code":"DE","type":"company","lineage":["https://openalex.org/I2799978770"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Gustavo L. Lopes","raw_affiliation_strings":["Instituto de Ciências Matemáticas e de Computação, Universidade de São Paulo Av. Trabalhador São-carlense,SP,Brazil"],"affiliations":[{"raw_affiliation_string":"Instituto de Ciências Matemáticas e de Computação, Universidade de São Paulo Av. Trabalhador São-carlense,SP,Brazil","institution_ids":["https://openalex.org/I2799978770"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029845097","display_name":"Moacir Antonelli Ponti","orcid":"https://orcid.org/0000-0003-2059-9463"},"institutions":[{"id":"https://openalex.org/I2799978770","display_name":"X-Fab (Germany)","ror":"https://ror.org/030bh9196","country_code":"DE","type":"company","lineage":["https://openalex.org/I2799978770"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Moacir A. Ponti","raw_affiliation_strings":["Instituto de Ciências Matemáticas e de Computação, Universidade de São Paulo Av. Trabalhador São-carlense,SP,Brazil"],"affiliations":[{"raw_affiliation_string":"Instituto de Ciências Matemáticas e de Computação, Universidade de São Paulo Av. Trabalhador São-carlense,SP,Brazil","institution_ids":["https://openalex.org/I2799978770"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042377165","display_name":"Maria Cristina Ferreira de Oliveira","orcid":"https://orcid.org/0000-0002-4729-5104"},"institutions":[{"id":"https://openalex.org/I2799978770","display_name":"X-Fab (Germany)","ror":"https://ror.org/030bh9196","country_code":"DE","type":"company","lineage":["https://openalex.org/I2799978770"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maria Cristina F. Oliveira","raw_affiliation_strings":["Instituto de Ciências Matemáticas e de Computação, Universidade de São Paulo Av. Trabalhador São-carlense,SP,Brazil"],"affiliations":[{"raw_affiliation_string":"Instituto de Ciências Matemáticas e de Computação, Universidade de São Paulo Av. Trabalhador São-carlense,SP,Brazil","institution_ids":["https://openalex.org/I2799978770"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5109644474"],"corresponding_institution_ids":["https://openalex.org/I2799978770"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32698272,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9675999879837036,"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":0.9675999879837036,"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/T10659","display_name":"Marine animal studies overview","score":0.00839999970048666,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11541","display_name":"Neuroendocrine regulation and behavior","score":0.00559999980032444,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9495999813079834},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6995000243186951},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.613099992275238},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5774999856948853},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4871000051498413},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4738999903202057},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4652000069618225},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3937999904155731}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9495999813079834},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6995000243186951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6866999864578247},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.613099992275238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.59579998254776},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5774999856948853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5288000106811523},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4871000051498413},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4738999903202057},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.3197000026702881},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.28139999508857727},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sibgrapi67909.2025.11223394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sibgrapi67909.2025.11223394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 38th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2000982976","https://openalex.org/W2101807845","https://openalex.org/W2784076614","https://openalex.org/W2899201823","https://openalex.org/W2963812188","https://openalex.org/W3000616311","https://openalex.org/W3033723397","https://openalex.org/W3096725570","https://openalex.org/W3097686148","https://openalex.org/W3103649165","https://openalex.org/W3105563334","https://openalex.org/W3124915800","https://openalex.org/W3199145413","https://openalex.org/W4206734067","https://openalex.org/W4309293828","https://openalex.org/W4389430009","https://openalex.org/W4389524160","https://openalex.org/W4411201749"],"related_works":[],"abstract_inverted_index":{"Passive":[0],"Acoustic":[1],"Monitoring":[2],"(PAM)":[3],"offers":[4],"invaluable":[5],"ecological":[6],"insights,":[7],"but":[8],"classifying":[9],"animal":[10],"vocalizations":[11,77],"via":[12],"deep":[13],"learning":[14],"is":[15],"severely":[16],"hampered":[17],"by":[18],"pervasive":[19],"noise,":[20],"overlapping":[21],"sounds,":[22],"and":[23,46,52,65,86],"critical":[24],"mislabeling":[25],"in":[26],"manually":[27],"annotated":[28],"training":[29,56,92],"data.":[30],"This":[31],"study":[32],"systematically":[33],"evaluates":[34],"the":[35,87],"impact":[36],"of":[37,89],"spectrogram":[38],"generation":[39],"strategies,":[40],"diverse":[41],"background":[42,83],"noise":[43,84],"reduction":[44],"techniques,":[45],"a":[47,96],"novel":[48],"approach":[49],"to":[50],"identify":[51],"remove":[53],"potentially":[54,90],"mislabeled":[55],"instances":[57],"on":[58],"ecoacoustic":[59,104],"classification":[60],"performance.":[61],"Experiments":[62],"with":[63,71],"ResNet":[64],"ViT":[66],"architectures":[67],"reveal":[68],"that":[69],"spectrograms":[70],"tightly":[72],"bounded":[73],"timefrequency":[74],"windows":[75],"around":[76],"dramatically":[78],"improve":[79],"classification.":[80],"Surprisingly,":[81],"both":[82],"removal":[85],"exclusion":[88],"noisy":[91],"labels":[93],"yielded":[94],"only":[95],"limited":[97],"impact.":[98],"These":[99],"findings":[100],"critically":[101],"redirect":[102],"future":[103],"efforts":[105],"towards":[106],"optimizing":[107],"vocalization":[108],"isolation.":[109]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-11T00:00:00"}