SM4在被動(dòng)聲學(xué)監(jiān)測(cè)中新熱帶無尾目鳥類識(shí)別基準(zhǔn)數(shù)據(jù)集中的應(yīng)用
Abstract
Global change is predicted to induce shifts in anuran acoustic behavior, which can be studied through passive acoustic monitoring (PAM). Understanding changes in calling behavior requires automatic identification of anuran species, which is challenging due to the particular characteristics of neotropical soundscapes. In this paper, we introduce a large-scale multi-species dataset of anuran amphibians calls recorded by PAM, that comprises 27hours of expert annotations for 42 different species from two Brazilian biomes. We provide open access to the dataset, including the raw recordings, experimental setup code, and a benchmark with a baseline model of the fine-grained categorization problem. Additionally, we highlight the challenges of the dataset to encourage machine learning researchers to solve the problem of anuran call identification towards conservation policy. All our experiments and resources have been made available at https://soundclim.github.io/anuraweb/.
摘要：
全球變化預(yù)計(jì)會(huì)引起無尾聲波行為的變化，這可以通過被動(dòng)聲學(xué)監(jiān)測(cè)（PAM）來研究。了解呼喚行為的變化需要自動(dòng)識(shí)別無尾目動(dòng)物物種，由于新熱帶音景的特殊特征，這是一個(gè)挑戰(zhàn)。本文介紹了PAM記錄的無尾兩棲動(dòng)物叫聲的大規(guī)模多物種數(shù)據(jù)集，其中包括來自巴西兩個(gè)生物群落的42個(gè)不同物種的27小時(shí)專家注釋。我們提供對(duì)數(shù)據(jù)集的開放訪問，包括原始記錄、實(shí)驗(yàn)設(shè)置代碼和具有細(xì)粒度分類問題基線模型的基準(zhǔn)。此外，我們強(qiáng)調(diào)了數(shù)據(jù)集的挑戰(zhàn)，以鼓勵(lì)機(jī)器學(xué)習(xí)研究人員解決針對(duì)保護(hù)政策的anuran呼叫識(shí)別問題。我們所有的實(shí)驗(yàn)和資源都在https://soundclim.github.io/anuraweb/上面.
關(guān)鍵詞：SM4聲音記錄器，鳥鳴叫監(jiān)測(cè)，Wildlife Acoustics，野外動(dòng)物聲音監(jiān)測(cè)，鳥類監(jiān)測(cè)
