WhAM：迈向 sperm 尾声的翻译模型
WhAM: Towards A Translative Model of Sperm Whale Vocalization
AI总结：
WhAM是一种基于transformer的模型，能够从音频提示生成高保真的抹香鲸咔嗒声，通过微调预训练的VampNet模型，实现了在节奏、社会单位和元音分类等任务上的优异表现。
摘要：
抹香鲸通过短序列的咔嗒声进行交流，称为codas。我们提出了WhAM（Whale Acoustics Model），第一个基于transformer的模型，能够从任何音频提示生成合成的sperm whale codas。WhAM通过在音乐音频上预训练的masked acoustic token模型VampNet上进行微调构建，使用了过去二十年收集的10,000个codas记录。通过迭代的masked token预测，WhAM生成高保真的合成codas，保留了源录音的关键声学特征。我们通过Fréchet Audio Distance和与专家海洋生物学家的感知研究评估WhAM的合成codas。在下游分类任务，包括节奏、社会单位和元音分类中，WhAM学习的表示在训练目标为生成而非分类的情况下，仍取得了优异的性能。我们的代码可在https://github.com/Project-CETI/wham获取。
英文摘要：
Sperm whales communicate in short sequences of clicks known as codas. We present WhAM (Whale Acoustics Model), the first transformer-based model capable of generating synthetic sperm whale codas from any audio prompt. WhAM is built by finetuning VampNet, a masked acoustic token model pretrained on musical audio, using 10k coda recordings collected over the past two decades. Through iterative masked token prediction, WhAM generates high-fidelity synthetic codas that preserve key acoustic features of the source recordings. We evaluate WhAM's synthetic codas using Fréchet Audio Distance and through perceptual studies with expert marine biologists. On downstream classification tasks including rhythm, social unit, and vowel classification, WhAM's learned representations achieve strong performance, despite being trained for generation rather than classification. Our code is available at https://github.com/Project-CETI/wham
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
