相关论文: SepPrune: Structured Pruning for Efficient Deep Sp…

Deep learning models, especially convolutional neural networks (CNNs), have shown considerable promise for biomedical signals such as EEG-based seizure detection. However, these models come with challenges, primarily due to their size and…

Automatic Speech Recognition models require large amount of speech data for training, and the collection of such data often leads to privacy concerns. Federated learning has been widely used and is considered to be an effective…

Deep pre-trained Transformer models have achieved state-of-the-art results over a variety of natural language processing (NLP) tasks. By learning rich language knowledge with millions of parameters, these models are usually…

We propose Cluster Pruning (CUP) for compressing and accelerating deep neural networks. Our approach prunes similar filters by clustering them based on features derived from both the incoming and outgoing weight connections. With CUP, we…

Mobile devices run deep learning models for various purposes, such as image classification and speech recognition. Due to the resource constraints of mobile devices, researchers have focused on either making a lightweight deep neural…

Model compression is crucial for deployment of neural networks on devices with limited computational and memory resources. Many different methods show comparable accuracy of the compressed model and similar compression rates. However, the…

Recently there has been a lot of work on pruning filters from deep convolutional neural networks (CNNs) with the intention of reducing computations.The key idea is to rank the filters based on a certain criterion (say, l1-norm) and retain…

Domain-specific embedding models have shown promise for applications that require specialized semantic understanding, such as coding agents and financial retrieval systems, often achieving higher performance gains than general models.…

Neural network pruning serves as a critical technique for enhancing the efficiency of deep learning models. Unlike unstructured pruning, which only sets specific parameters to zero, structured pruning eliminates entire channels, thus…

Deep neural network (DNN) based speech enhancement models have attracted extensive attention due to their promising performance. However, it is difficult to deploy a powerful DNN in real-time applications because of its high computational…

Unstructured pruning reduces the memory footprint in deep neural networks (DNNs). Recently, researchers proposed different types of structural pruning intending to reduce also the computation complexity. In this work, we first suggest a new…

Although multi-task deep neural network (DNN) models have computation and storage benefits over individual single-task DNN models, they can be further optimized via model compression. Numerous structured pruning methods are already…

In recent years, deep learning-based single-channel speech separation has improved considerably, in large part driven by increasingly compute- and parameter-efficient neural network architectures. Most such architectures are, however,…

Speaker-independent speech separation has achieved remarkable performance in recent years with the development of deep neural network (DNN). Various network architectures, from traditional convolutional neural network (CNN) and recurrent…

Pruning, the task of sparsifying deep neural networks, received increasing attention recently. Although state-of-the-art pruning methods extract highly sparse models, they neglect two main challenges: (1) the process of finding these sparse…

Channel pruning, which seeks to reduce the model size by removing redundant channels, is a popular solution for deep networks compression. Existing channel pruning methods usually conduct layer-wise channel selection by directly minimizing…

We study model pruning methods applied to Transformer-based neural network language models for automatic speech recognition. We explore three aspects of the pruning frame work, namely criterion, method and scheduler, analyzing their…

Large language models(LLMs) have garnered significant attention and demonstrated impressive capabilities in a wide range of applications. However, due to their enormous computational costs, the deployment and application of LLMs are often…

Deep convolutional neural networks have liberated its extraordinary power on various tasks. However, it is still very challenging to deploy state-of-the-art models into real-world applications due to their high computational complexity. How…

Pruning is a widely used technique for reducing the size of deep neural networks while maintaining their performance. However, such a technique, despite being able to massively compress deep models, is hardly able to remove entire layers…