相关论文: Dynamic nsNet2: Efficient Deep Noise Suppression w…

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. To improve robustness of speaker recognition system performance in…

Speech foundation models have significantly advanced various speech-related tasks by providing exceptional representation capabilities. However, their high-dimensional output features often create a mismatch with downstream task models,…

This paper gives an overview of our ongoing work on the design space exploration of efficient deep neural networks (DNNs). Specifically, we cover two aspects: (1) static architecture design efficiency and (2) dynamic model execution…

We present QuickNet, a fast and accurate network architecture that is both faster and significantly more accurate than other fast deep architectures like SqueezeNet. Furthermore, it uses less parameters than previous networks, making it…

Distributed inference techniques can be broadly classified into data-distributed and model-distributed schemes. In data-distributed inference (DDI), each worker carries the entire deep neural network (DNN) model but processes only a subset…

As deep neural networks continue to expand and become more complex, most edge devices are unable to handle their extensive processing requirements. Therefore, the concept of distributed inference is essential to distribute the neural…

The deployment of Deep Neural Networks in energy-constrained environments, such as Energy Harvesting Wireless Sensor Networks, presents unique challenges, primarily due to the intermittent nature of power availability. To address these…

Present-day Deep Reinforcement Learning (RL) systems show great promise towards building intelligent agents surpassing human-level performance. However, the computational complexity associated with the underlying deep neural networks (DNNs)…

Physical computing has the potential to enable widespread embodied intelligence by leveraging the intrinsic dynamics of complex systems for efficient sensing, processing, and interaction. While individual devices provide basic data…

State-of-the-art neural networks with early exit mechanisms often need considerable amount of training and fine tuning to achieve good performance with low computational cost. We propose a novel early exit technique, Early Exit Class Means…

Deep Ensembles are a simple, reliable, and effective method of improving both the predictive performance and uncertainty estimates of deep learning approaches. However, they are widely criticised as being computationally expensive, due to…

Pushing forward the compute efficacy frontier in deep learning is critical for tasks that require frequent model re-training or workloads that entail training a large number of models. We introduce SliceOut -- a dropout-inspired scheme…

Resource-constrained edge deployments demand AI solutions that balance high performance with stringent compute, memory, and energy limitations. In this survey, we present a comprehensive overview of the primary strategies for accelerating…

Machine learning models can solve complex tasks but often require significant computational resources during inference. This has led to the development of various post-training computation reduction methods that tackle this issue in…

Echo cancellation and noise reduction are essential for full-duplex communication, yet most existing neural networks have high computational costs and are inflexible in tuning model complexity. In this paper, we introduce time-frequency…

We introduce Dynamic Deep Neural Networks (D2NN), a new type of feed-forward deep neural network that allows selective execution. Given an input, only a subset of D2NN neurons are executed, and the particular subset is determined by the…

Recent progress in speech separation has been largely driven by advances in deep neural networks, yet their high computational and memory requirements hinder deployment on resource-constrained devices. A significant inefficiency in…

Large Deep Neural Networks (DNNs) are the backbone of today's artificial intelligence due to their ability to make accurate predictions when being trained on huge datasets. With advancing technologies, such as the Internet of Things,…

With its strong modeling capacity that comes from a multi-head and multi-layer structure, Transformer is a very powerful model for learning a sequential representation and has been successfully applied to speech separation recently.…

Raw deep neural network (DNN) performance is not enough; in real-world settings, computational load, training efficiency and adversarial security are just as or even more important. We propose to simultaneously tackle Performance,…