Related papers: Performance optimizations on deep noise suppressio…
Hardware-Software Co-Design is a highly successful strategy for improving performance of domain-specific computing systems. We argue for the application of the same methodology to deep learning; specifically, we propose to extend neural…
Background noise is a major source of quality impairments in Voice over Internet Protocol (VoIP) and Public Switched Telephone Network (PSTN) calls. Recent work shows the efficacy of deep learning for noise suppression, but the datasets…
State-of-the-art convolutional neural networks (CNNs) used in vision applications have large models with numerous weights. Training these models is very compute- and memory-resource intensive. Much research has been done on pruning or…
The growing energy and performance costs of deep learning have driven the community to reduce the size of neural networks by selectively pruning components. Similarly to their biological counterparts, sparse networks generalize just as…
Deep learning recommendation systems at scale have provided remarkable gains through increasing model capacity (i.e. wider and deeper neural networks), but it comes at significant training cost and infrastructure cost. Model pruning is an…
Spiking Neural Networks (SNNs) are a promising alternative to traditional deep learning methods since they perform event-driven information processing. However, a major drawback of SNNs is high inference latency. The efficiency of SNNs…
The advent of sparsity inducing techniques in neural networks has been of a great help in the last few years. Indeed, those methods allowed to find lighter and faster networks, able to perform more efficiently in resource-constrained…
As neural networks grow in size and complexity, inference speeds decline. To combat this, one of the most effective compression techniques -- channel pruning -- removes channels from weights. However, for multi-branch segments of a model,…
Convolutional neural networks (CNN) have achieved impressive performance on the wide variety of tasks (classification, detection, etc.) across multiple domains at the cost of high computational and memory requirements. Thus, leveraging CNNs…
We develop an approach to growing deep network architectures over the course of training, driven by a principled combination of accuracy and sparsity objectives. Unlike existing pruning or architecture search techniques that operate on…
As Deep Neural Networks (DNNs) rapidly advance in various fields, including speech verification, they typically involve high computational costs and substantial memory consumption, which can be challenging to manage on mobile systems.…
Although deep learning has made strides in the field of deep noise suppression, leveraging deep architectures on resource-constrained devices still proved challenging. Therefore, we present an early-exiting model based on nsNet2 that…
Structured pruning has been extensively studied on monolingual pre-trained language models and is yet to be fully evaluated on their multilingual counterparts. This work investigates three aspects of structured pruning on multilingual…
Neural architecture search (NAS) and network pruning are widely studied efficient AI techniques, but not yet perfect. NAS performs exhaustive candidate architecture search, incurring tremendous search cost. Though (structured) pruning can…
Pruning is a model compression method that removes redundant parameters in deep neural networks (DNNs) while maintaining accuracy. Most available filter pruning methods require complex treatments such as iterative pruning, features…
Deep Neural Networks are highly over-parameterized and the size of the neural networks can be reduced significantly after training without any decrease in performance. One can clearly see this phenomenon in a wide range of architectures…
The leap in performance in state-of-the-art computer vision methods is attributed to the development of deep neural networks. However it often comes at a computational price which may hinder their deployment. To alleviate this limitation,…
Convolutional neural networks (CNNs), such as the time-delay neural network (TDNN), have shown their remarkable capability in learning speaker embedding. However, they meanwhile bring a huge computational cost in storage size, processing,…
The unstructured sparsity after pruning poses a challenge to the efficient implementation of deep learning models in existing regular architectures like systolic arrays. On the other hand, coarse-grained structured pruning is suitable for…
With the increasing size of large language models, layer pruning has gained increased attention as a hardware-friendly approach for model compression. However, existing layer pruning methods struggle to simultaneously address key practical…