CallCleaner：从音频基础模型蒸馏出的19M参数动物叫声降噪工具
CallCleaner: Lightweight Bioacoustic Denoising from an Audio Foundation Model
野外录的鸟叫蛙叫总混着风声车声？这套开源的 CallCleaner 只有 19M 参数，笔记本 CPU 就能跑，降噪效果比 Biodenoising 多出 11 dB。做生物声学研究或环境监测的朋友可以直接下载权重本地用。
Meta 的通用音频分离基础模型 SAM-Audio 在动物叫声降噪任务上表现优于经典谱减门控和专用的无检测器神经降噪器，无需训练、只需用简单的动物 VAD 时间段作为提示即可。
研究团队随后将 SAM-Audio 蒸馏为 CallCleaner，一个仅 19M 参数的降噪器，不需要检测器，在笔记本 CPU 上运行速度约为实时 90 倍。与公开权重的领先神经降噪器 Biodenoising 相比，CallCleaner 在叫声周围留下的噪声少了 11 dB，并在 CPU 可运行的系统中推高了噪声去除与叫声保真度之间的帕累托前沿。
论文还指出 SI-SDR 指标在该场景下作用有限，因为它会惩罚重新生成的输出，且把噪声去除和叫声保真度混为一谈。CallCleaner 的代码和权重已开源，可在无专用硬件的本地环境对单一个体叫声录音做快速、私密的降噪。
CallCleaner: Lightweight Bioacoustic Denoising from an Audio Foundation Model
Many studies of animal vocalizations require clean recordings, but animals are usually recorded in the field, with background noise from weather, vehicles, and other animals. Animal vocalization denoising is challenged by the scarcity of clean training data and the extreme diversity of animal vocalizations. Classical spectral gates leave residual noise, especially without voice activity detection (VAD), while detector-free neural denoisers designed for bioacoustics remove less noise. We show that a general-purpose source separation foundation model, SAM-Audio, removes more noise than either of these types of methods, when used without training and prompted with time spans from a simple animal VAD. To turn this heavy method into a practical tool, we distill it into CallCleaner, a 19M-parameter denoiser that needs no detector and runs ~90x faster than real time on a laptop CPU. We find that SI-SDR has limited utility in our setting as it penalizes regenerated output and conflates noise removal with call fidelity, a trade-off our separate metrics reveal. CallCleaner leaves 11 dB less noise around the call than Biodenoising, the leading neural bioacoustic denoiser with public weights, and among fast, CPU-capable systems it pushes the Pareto frontier of noise removal vs. call fidelity, without requiring a detector. We release code and weights for CallCleaner, which enables fast, private, local denoising of single-caller recordings without specialized hardware.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include SAM-Audio, CallCleaner, 音频分离, 开源模型.
Source attribution: curated from arXiv cs.LG (@Michael Xie, Gašper Beguš, Morris Alper).