TinyBird-ML：一种用于鸟声分析与音节分类的超低功耗智能传感器节点
TinyBird-ML: An ultra-low Power Smart Sensor Node for Bird Vocalization Analysis and Syllable Classification
AI总结：
提出仅重1.4g的超低功耗可穿戴传感器节点TinyBird-ML，结合低延迟微型机器学习算法和节能软硬件设计，实现鸟声音节实时分类与无线传输，单电池续航达25小时。
摘要：
动物发声具有广泛的重要功能。尽管可以使用外部麦克风录制动物发声，但直接安装在动物背部的微型传感器能提供更多见解。我们提出了TinyBird-ML；这是一种仅重1.4 g的可穿戴传感器节点，用于采集、处理声学信号，并通过低功耗蓝牙将信号无线传输至主机系统。TinyBird-ML嵌入了用于歌曲音节分类的低延迟微型机器学习算法。为了优化TinyBird-ML在容错连续录音期间的电池寿命，我们提出了一种高效的固件和硬件设计。我们利用标准有损压缩方案来减少通过蓝牙天线发送的数据量，使电池寿命提高了70%，且对离线声音分析无负面影响。此外，通过在静默期间不传输信号，我们进一步提高了电池寿命。我们传感器的一个优势是，它通过直接在设备上处理声音而非将其流式传输到计算机，从而允许在微秒级范围内进行闭环实验。我们通过使用直接在传感器节点上运行的轻量级神经网络，以最小延迟和7%的音节错误率检测并分类歌曲音节，证明了这一能力。得益于我们节能的软硬件设计，在16 kHz采样率的连续操作下，该传感器节点在一节13号锌空气电池上可达到25小时的寿命。
英文摘要：
Animal vocalisations serve a wide range of vital functions. Although it is possible to record animal vocalisations with external microphones, more insights are gained from miniature sensors mounted directly on animals' backs. We present TinyBird-ML; a wearable sensor node weighing only 1.4 g for acquiring, processing, and wirelessly transmitting acoustic signals to a host system using Bluetooth Low Energy. TinyBird-ML embeds low-latency tiny machine learning algorithms for song syllable classification. To optimize battery lifetime of TinyBird-ML during fault-tolerant continuous recordings, we present an efficient firmware and hardware design. We make use of standard lossy compression schemes to reduce the amount of data sent over the Bluetooth antenna, which increases battery lifetime by 70% without negative impact on offline sound analysis. Furthermore, by not transmitting signals during silent periods, we further increase battery lifetime. One advantage of our sensor is that it allows for closed-loop experiments in the microsecond range by processing sounds directly on the device instead of streaming them to a computer. We demonstrate this capability by detecting and classifying song syllables with minimal latency and a syllable error rate of 7%, using a light-weight neural network that runs directly on the sensor node itself. Thanks to our power-saving hardware and software design, during continuous operation at a sampling rate of 16 kHz, the sensor node achieves a lifetime of 25 hours on a single size 13 zinc-air battery.
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。
