paper-with-me

홈 › Papers

MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection

2020-10-26

We present MarbleNet, an end-to-end neural network for Voice Activity Detection (VAD). MarbleNet is a deep residual network composed from blocks of 1D time-channel separable convolution, batch-normalization, ReLU and dropout layers. When compared to a state-of-the-art VAD model, MarbleNet is able to achieve similar performance with roughly 1/10-th the parameter cost. We further conduct extensive ablation studies on different training methods and choices of parameters in order to study the robustness of MarbleNet in real-world VAD tasks.

📄 PDF Abstract BibTeX arXiv:2010.13886

Code (0)

등록된 구현이 없습니다.

Tasks

Action DetectionActivity Detection

Similar Papers 제목 키워드 기반

Depthwise-STFT based separable Convolutional Neural Networks

2020-01-27 · Sudhakar Kumawat, Shanmuganathan Raman

In this paper, we propose a new convolutional layer called Depthwise-STFT Separable layer that can serve as an alternative to the standard depthwise separable convolutional layer. The construction of the proposed layer i…

image-classificationImage ClassificationPosition

Audio-to-Image Encoding for Improved Voice Characteristic Detection Using Deep Convolutional Neural Networks

2025-03-07 · Youness Atif

This paper introduces a novel audio-to-image encoding framework that integrates multiple dimensions of voice characteristics into a single RGB image for speaker recognition. In this method, the green channel encodes raw …

Speaker Recognition

Design of Image Matched Non-Separable Wavelet using Convolutional Neural Network

2016-12-15 · Naushad Ansari, Anubha Gupta, Rahul Duggal

Image-matched nonseparable wavelets can find potential use in many applications including image classification, segmen- tation, compressive sensing, etc. This paper proposes a novel design methodology that utilizes convo…

Compressive SensingGeneral Classificationimage-classificationImage Classification

MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition

2020-04-21

We present an MatchboxNet - an end-to-end neural network for speech command recognition. MatchboxNet is a deep residual network composed from blocks of 1D time-channel separable convolution, batch-normalization, ReLU and…

Data AugmentationTime Series Analysis

PrimeK-Net: Multi-scale Spectral Learning via Group Prime-Kernel Convolutional Neural Networks for Single Channel Speech Enhancement

2025-02-27 · Zizhen Lin, Junyu Wang, Ruili Li, Fei Shen 외

Single-channel speech enhancement is a challenging ill-posed problem focused on estimating clean speech from degraded signals. Existing studies have demonstrated the competitive performance of combining convolutional neu…

Computational EfficiencySpeech Enhancement