Related papers: Real-time Denoising and Dereverberation with Tiny …

Diffusion-based image generation models have achieved great success in recent years by showing the capability of synthesizing high-quality content. However, these models contain a huge number of parameters, resulting in a significantly…

Neural network quantization and pruning are two techniques commonly used to reduce the computational complexity and memory footprint of these models for deployment. However, most existing pruning strategies operate on full-precision and…

Convolutional neural networks (CNNs) with dilated filters such as the Wavenet or the Temporal Convolutional Network (TCN) have shown good results in a variety of sequence modelling tasks. However, efficiently modelling long-term…

Network-based transfer learning allows the reuse of deep learning features with limited data, but the resulting models can be unnecessarily large. Although network pruning can improve inference efficiency, existing algorithms usually…

Modern deep neural networks, particularly recent large language models, come with massive model sizes that require significant computational and storage resources. To enable the deployment of modern models on resource-constrained…

Online Speech Enhancement was mainly reserved for predictive models. A key advantage of these models is that for an incoming signal frame from a stream of data, the model is called only once for enhancement. In contrast, generative Speech…

Always-on machine learning models require a very low memory and compute footprint. Their restricted parameter count limits the model's capacity to learn, and the effectiveness of the usual training algorithms to find the best parameters.…

Real-time image segmentation is a key enabler for AR/VR, robotics, drones, and autonomous systems, where tight accuracy, latency, and energy budgets must be met on resource-constrained edge devices. While U-Net offers a favorable balance of…

Disfluency detection models now approach high accuracy on English text. However, little exploration has been done in improving the size and inference time of the model. At the same time, automatic speech recognition (ASR) models are moving…

We present DiffusionBERT, a new generative masked language model based on discrete diffusion models. Diffusion models and many pre-trained language models have a shared training objective, i.e., denoising, making it possible to combine the…

In the era of AIGC, the demand for low-budget or even on-device applications of diffusion models emerged. In terms of compressing the Stable Diffusion models (SDMs), several approaches have been proposed, and most of them leveraged the…

The ever-increasing size of large language models (LLMs) presents significant challenges for deployment due to their heavy computational and memory requirements. Current model pruning techniques attempt to alleviate these issues by relying…

Considering the increased workload in pathology laboratories today, automated tools such as artificial intelligence models can help pathologists with their tasks and ease the workload. In this paper, we are proposing a segmentation model…

Deep Neural Networks (DNNs) are usually over-parameterized, causing excessive memory and interconnection cost on the hardware platform. Existing pruning approaches remove secondary parameters at the end of training to reduce the model size;…

Distant speech recognition is a challenge, particularly due to the corruption of speech signals by reverberation caused by large distances between the speaker and microphone. In order to cope with a wide range of reverberations in…

Convolutional Neural Networks (CNN) increase depth by stacking convolutional layers, and deeper network models perform better in image recognition. Empirical research shows that simply stacking convolutional layers does not make the network…

Machine learning-based applications are increasingly prevalent in IoT devices. The power and storage constraints of these devices make it particularly challenging to run modern neural networks, limiting the number of new applications that…

With the development of deep learning, medical image processing has been widely used to assist clinical research. This paper focuses on the denoising problem of low-dose computed tomography using deep learning. Although low-dose computed…

Deep Learning plays a significant role in assisting humans in many aspects of their lives. As these networks tend to get deeper over time, they extract more features to increase accuracy at the cost of additional inference latency. This…

Recent advances in neural text-to-speech (TTS) models bring thousands of TTS applications into daily life, where models are deployed in cloud to provide services for customs. Among these models are diffusion probabilistic models (DPMs),…