PulseAugur
实时 10:09:21
English(EN) Adaptive Speech-to-Spike Encoding for Spiking Neural Networks

新型编码器提升神经形态语音处理精度

研究人员开发了一种新颖的可学习残差语音到脉冲编码器,旨在改进神经形态语音处理。该编码器与循环式渗漏整合发放(Recurrent Leaky Integrate-and-Fire)骨干网络进行端到端训练,解决了连续声学信号与脉冲神经网络(SNNs)中离散事件驱动处理之间的根本不匹配问题。该方法在 Google Speech Commands v2 基准测试上达到了高达 94.97% 的准确率,其参数高效变体达到了 89.8%。分析表明,该编码器学习的是与任务对齐的脉冲表示,而非直接信号重建,从而增强了类别可分性。 AI

影响 提高神经形态语音处理系统的效率和准确性。

排序理由 该集群包含一篇详细介绍脉冲神经网络新方法的学术论文。

在 arXiv cs.NE (Neural & Evolutionary) 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Taharim Rahman Anon, Jakaria Islam Emon ·

    Adaptive Speech-to-Spike Encoding for Spiking Neural Networks

    arXiv:2606.19039v1 Announce Type: cross Abstract: The mismatch between continuous acoustic signals and discrete event-driven processing remains a fundamental bottleneck for neuromorphic speech processing. Current systems typically rely on fixed spike encoders, forcing downstream …

  2. arXiv cs.NE (Neural & Evolutionary) TIER_1 English(EN) · Jakaria Islam Emon ·

    用于脉冲神经网络的自适应语音到脉冲编码

    The mismatch between continuous acoustic signals and discrete event-driven processing remains a fundamental bottleneck for neuromorphic speech processing. Current systems typically rely on fixed spike encoders, forcing downstream Spiking Neural Networks (SNNs) to compensate for n…