paper-with-me

홈 › Papers

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 dropout layers. MatchboxNet reaches state-of-the-art accuracy on the Google Speech Commands dataset while having significantly fewer parameters than similar models. The small footprint of MatchboxNet makes it an attractive candidate for devices with limited computational resources. The model is highly scalable, so model accuracy can be improved with modest additional memory and compute. Finally, we show how intensive data augmentation using an auxiliary noise dataset improves robustness in the presence of background noise.

📄 PDF Abstract BibTeX arXiv:2004.08531

Code (1)

google-research/google-research/tree/master/kws_streaming tf

Tasks

Data AugmentationTime Series Analysis

Similar Papers 제목 키워드 기반

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 dro…

Action DetectionActivity Detection

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

Channel Compression: Rethinking Information Redundancy among Channels in CNN Architecture

2020-07-02 · Jinhua Liang, Tao Zhang, Guoqing Feng

Model compression and acceleration are attracting increasing attentions due to the demand for embedded devices and mobile applications. Research on efficient convolutional neural networks (CNNs) aims at removing feature …

Acoustic Scene ClassificationEvent Detectionimage-classificationImage Classification+3

Deep Residual Axial Networks

2023-01-11 · Nazmul Shahadat, Anthony S. Maida

While convolutional neural networks (CNNs) demonstrate outstanding performance on computer vision tasks, their computational costs remain high. Several techniques are used to reduce these costs, like reducing channel cou…

image-classificationImage ClassificationImage Super-ResolutionSuper-Resolution

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