paper-with-me

홈 › Papers

SNDCNN: Self-normalizing deep CNNs with scaled exponential linear units for speech recognition

2019-10-04 · Zhen Huang, Tim Ng, Leo Liu, Henry Mason, Xiaodan Zhuang, Daben Liu

Very deep CNNs achieve state-of-the-art results in both computer vision and speech recognition, but are difficult to train. The most popular way to train very deep CNNs is to use shortcut connections (SC) together with batch normalization (BN). Inspired by Self- Normalizing Neural Networks, we propose the self-normalizing deep CNN (SNDCNN) based acoustic model topology, by removing the SC/BN and replacing the typical RELU activations with scaled exponential linear unit (SELU) in ResNet-50. SELU activations make the network self-normalizing and remove the need for both shortcut connections and batch normalization. Compared to ResNet- 50, we can achieve the same or lower (up to 4.5% relative) word error rate (WER) while boosting both training and inference speed by 60%-80%. We also explore other model inference optimization schemes to further reduce latency for production use.

📄 PDF Abstract BibTeX arXiv:1910.01992

Code (0)

등록된 구현이 없습니다.

Tasks

Inference Optimizationspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
Average Pooling 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Residual Connection 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Similar Papers 제목 키워드 기반

Effectiveness of Scaled Exponentially-Regularized Linear Units (SERLUs)

2018-07-26 · G. Zhang, H. Li

Recently, self-normalizing neural networks (SNNs) have been proposed with the intention to avoid batch or weight normalization. The key step in SNNs is to properly scale the exponential linear unit (referred to as SELU) …

Frame-level SpecAugment for Deep Convolutional Neural Networks in Hybrid ASR Systems

2020-12-07 · Xinwei Li, Yuanyuan Zhang, Xiaodan Zhuang, Daben Liu

Inspired by SpecAugment -- a data augmentation method for end-to-end ASR systems, we propose a frame-level SpecAugment method (f-SpecAugment) to improve the performance of deep convolutional neural networks (CNN) for hyb…

Data Augmentation

Self-Normalizing Neural Networks

2017-06-08 · NeurIPS 2017 12 · Günter Klambauer, Thomas Unterthiner, Andreas Mayr, Sepp Hochreiter

Deep Learning has revolutionized vision via convolutional neural networks (CNNs) and natural language processing via recurrent neural networks (RNNs). However, success stories of Deep Learning with standard feed-forward …

AstronomyBIG-bench Machine LearningDrug DiscoveryPulsar Prediction

Effectiveness of Self Normalizing Neural Networks for Text Classification

2019-05-03 · Avinash Madasu, Vijjini Anvesh Rao

Self Normalizing Neural Networks(SNN) proposed on Feed Forward Neural Networks(FNN) outperform regular FNN architectures in various machine learning tasks. Particularly in the domain of Computer Vision, the activation fu…

ClassificationGeneral Classificationtext-classificationText Classification

A Multi-Task Self-Normalizing 3D-CNN to Infer Tuberculosis Radiological Manifestations

2019-07-29

We propose a learning method well-suited to infer the presence of Tuberculosis (TB) manifestations on Computer Tomography (CT) scans mimicking the radiologist reports. Latent features are extracted from the CT volumes em…

Multi-class ClassificationMulti-Task Learning