Evelina León

Automatic classification of Furnariidae species from the Paranaense Littoral region using speech-related features and machine learning

Over the last years, researchers have addressed the automatic classification of calling bird species. This is important for achieving more exhaustive environmental monitoring and for managing natural resources. Vocalisations help to identify new species, their natural history and macro-systematic relations, while computer systems allow the bird recognition process to be sped up and improved. In this study, an approach that uses state-of-the-art features designed for speech and speaker state recognition is presented. A method for voice activity detection was employed previous to feature extraction. Our analysis includes several classification techniques (multilayer perceptrons, support vector machines and random forest) and compares their performance using different configurations to define the best classification method. The experimental results were validated in a cross-validation scheme, using 25 species of the family Furnariidae that inhabit the Paranaense Littoral region of Argentina (South America). The results show that a high classification rate, close to 90%, is obtained for this family in this Furnariidae group using the proposed features and classifiers.

Song structure of the golden-billed saltator (Saltator aurantiirostris) in the middle Parana river floodplain

Bird communication is a growing field of study in ethology and evolutionary biology; however, most known studies were conducted only in the northern hemisphere. We measured six temporal and structural features of golden-billed saltator (Saltator aurantiirostris) song and recorded 57 vocalizations at Parque San Martín reserve (Argentina). Results indicated that the prelude represented between two and four syllables, while the trill was composed of one to three. The complete song always contained six syllables. Maximum and minimum frequencies were higher in the trill. The duration of prelude and trill did not differ between vocalizations. Modifications and differences observed in vocalizations may be explained by the acoustic adaptation hypothesis, which predicts higher frequencies in open habitats. Our results broaden and supplement the data available for this species in Argentina, representing useful information for studies intended to assess the effect of different habitats on birds vocalizations in southern South America.

Reproductive Biology of Striated Heron (Butorides striata) in Argentina

Abstract The reproductive biology of the Striated Heron (Butorides striata) was studied in the lagoon of the Reserve of the Universidad Nacional del Litoral, Santa Fe, Argentina, during two breeding seasons: September 2012–February 2013 (n = 77) and September 2013–March 2014 (n = 125). All nests (n = 202) were built on waxy-leaf nightshade (Solanum glaucophyllum) at 0.99 ± 0.27 m above water level. The incubation period was 20–23 (21.71 ± 1.57) days; laying and hatching took place on successive days. An average of 2.63 ± 0.60 (Range = 2–4) opaque pale blue eggs were recorded per nest. Length, width and weight of eggs did not differ between seasons. Double (n = 43) and triple (n = 47) broods were recorded. A total of 631 eggs were monitored; no differences were detected in breeding, hatching, nesting, or fledging success between seasons. The time spent by chicks in the nest was 14.6 ± 2.16 days, and the average number of chicks per nest was 2.15 ± 0.55. Age-specific mortality rate for eggs was 22% and 38% and for chicks 47% and 35% for the first and second seasons, respectively. Sixty-one percent of nest failures were related to the disappearance of eggs or chicks from the nests, possibly due to predation or climatic factors.