• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Asia and South Pacific Design Automation Conference >Low-power neuromorphic speech recognition engine with coarse-grain sparsity
【24h】

Low-power neuromorphic speech recognition engine with coarse-grain sparsity

机译：具有稀疏稀疏性的低功率神经形态语音识别引擎

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In recent years, we have seen a surge of interest in neuromorphic computing and its hardware design for cognitive applications. In this work, we present new neuromorphic architecture, circuit, and device co-designs that enable spike-based classification for speech recognition task. The proposed neuromorphic speech recognition engine supports a sparsely connected deep spiking network with coarse granularity, leading to large memory reduction with minimal index information. Simulation results show that the proposed deep spiking neural network accelerator achieves phoneme error rate (PER) of 20.5% for TIMIT database, and consume 2.57mW in 40nm CMOS for real-time performance. To alleviate the memory bottleneck, the usage of non-volatile memory is also evaluated and discussed.
机译：近年来，我们看到了对神经形态计算及其用于认知应用的硬件设计的兴趣激增。在这项工作中，我们提出了新的神经形态架构，电路和设备协同设计，它们可以为语音识别任务提供基于尖峰的分类。所提出的神经形态语音识别引擎支持具有稀疏粒度的稀疏连接的深度尖峰网络，从而导致在减少索引信息的情况下减少大量内存。仿真结果表明，所提出的深尖刺神经网络加速器为TIMIT数据库提供了20.5％的音素错误率（PER），并在40nm CMOS中消耗了2.57mW的实时性能。为了减轻存储瓶颈，还对非易失性存储器的使用进行了评估和讨论。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号