paper-with-me

Papers

Sparse Binarization for Fast Keyword Spotting

2024-06-09 · Jonathan Svirsky, Uri Shaham, Ofir Lindenbaum

With the increasing prevalence of voice-activated devices and applications, keyword spotting (KWS) models enable users to interact with technology hands-free, enhancing convenience and accessibility in various contexts. Deploying KWS models on edge devices, such as smartphones and embedded systems, offers significant benefits for real-time applications, privacy, and bandwidth efficiency. However, these devices often possess limited computational power and memory. This necessitates optimizing neural network models for efficiency without significantly compromising their accuracy. To address these challenges, we propose a novel keyword-spotting model based on sparse input representation followed by a linear classifier. The model is four times faster than the previous state-of-the-art edge device-compatible model with better accuracy. We show that our method is also more robust in noisy environments while being fast. Our code is available at: https://github.com/jsvir/sparknet.

📄 PDF Abstract BibTeX arXiv:2406.06634

Code (1)

jsvir/sparknet 공식 구현 pytorch

Tasks

BinarizationKeyword Spotting

Similar Papers 제목 키워드 기반

WSRNet: Joint Spotting and Recognition of Handwritten Words

2020-08-17 · George Retsinas, Giorgos Sfikas, Petros Maragos

In this work, we present a unified model that can handle both Keyword Spotting and Word Recognition with the same network architecture. The proposed network is comprised of a non-recurrent CTC branch and a Seq2Seq branch…

BinarizationKeyword Spotting

A Channel-Pruned and Weight-Binarized Convolutional Neural Network for Keyword Spotting

2019-09-12 · Jiancheng Lyu, Spencer Sheen

We study channel number reduction in combination with weight binarization (1-bit weight precision) to trim a convolutional neural network for a keyword spotting (classification) task. We adopt a group-wise splitting meth…

BinarizationGeneral ClassificationKeyword Spotting

BiFSMN: Binary Neural Network for Keyword Spotting

2022-02-14 · Haotong Qin, Xudong Ma, Yifu Ding, Xiaoyang Li 외

The deep neural networks, such as the Deep-FSMN, have been widely studied for keyword spotting (KWS) applications. However, computational resources for these networks are significantly constrained since they usually run …

BinarizationKeyword Spotting

BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance

2022-11-13 · Haotong Qin, Xudong Ma, Yifu Ding, Xiaoyang Li 외

Deep neural networks, such as the Deep-FSMN, have been widely studied for keyword spotting (KWS) applications while suffering expensive computation and storage. Therefore, network compression technologies like binarizati…

BinarizationKeyword Spotting

Fast ASR-free and almost zero-resource keyword spotting using DTW and CNNs for humanitarian monitoring

2018-06-25 · Raghav Menon, Herman Kamper, John Quinn, Thomas Niesler

We use dynamic time warping (DTW) as supervision for training a convolutional neural network (CNN) based keyword spotting system using a small set of spoken isolated keywords. The aim is to allow rapid deployment of a ke…

Dynamic Time WarpingHumanitarianKeyword SpottingTemplate Matching