paper-with-me

Papers

Neural ODE with Temporal Convolution and Time Delay Neural Networks for Small-Footprint Keyword Spotting

2020-08-01 · Hiroshi Fuketa, Yukinori Morita

In this paper, we propose neural network models based on the neural ordinary differential equation (NODE) for small-footprint keyword spotting (KWS). We present techniques to apply NODE to KWS that make it possible to adopt Batch Normalization to NODE-based network and to reduce the number of computations during inference. Finally, we show that the number of model parameters of the proposed model is smaller by 68% than that of the conventional KWS model.

📄 PDF Abstract BibTeX arXiv:2008.00209

Code (1)

fkhiro/kws-ode 공식 구현 pytorch

Tasks

Keyword SpottingSmall-Footprint Keyword Spotting

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

Combining Convolution and Delay Learning in Recurrent Spiking Neural Networks

2026-04-17 · Lúcio Folly Sanches Zebendo, Eleonora Cicciarella, Michele Rossi arxiv

Spiking neural networks (SNNs) are rapidly gaining momentum as an alternative to conventional artificial neural networks in resource constrained edge systems. In this work, we continue a recent research line on recurrent…

Audio Classification

Small-Footprint Keyword Spotting with Multi-Scale Temporal Convolution

2020-10-20 · Ximin Li, Xiaodong Wei, Xiaowei Qin

Keyword Spotting (KWS) plays a vital role in human-computer interaction for smart on-device terminals and service robots. It remains challenging to achieve the trade-off between small footprint and high accuracy for KWS …

Efficient Neural NetworkKeyword SpottingSmall-Footprint Keyword Spotting

mGRADE: Minimal Recurrent Gating Meets Delay Convolutions for Lightweight Sequence Modeling

2025-07-02 · Tristan Torchet, Christian Metzner, Karthik Charan Raghunathan, Jimmy Weber 외 arxiv

Multi-timescale sequence modeling relies on capturing both local fast dynamics and global slow context; yet, maintaining these capabilities under the strict memory constraints common to edge devices remains an open chall…

Audio Classification

Discrete Function Bases and Convolutional Neural Networks

2021-03-09 · Andreas Stöckel

We discuss the notion of "discrete function bases" with a particular focus on the discrete basis derived from the Legendre Delay Network (LDN). We characterize the performance of these bases in a delay computation task, …

Spatiotemporal Propagation Learning for Network-Wide Flight Delay Prediction

2022-07-14 · Yuankai Wu, Hongyu Yang, Yi Lin, Hong Liu

Demystifying the delay propagation mechanisms among multiple airports is fundamental to precise and interpretable delay prediction, which is crucial during decision-making for all aviation industry stakeholders. The prin…

Decision MakingPredictionTime Series Analysis