Related papers: Precision Scaling of Neural Networks for Efficient…

Recurrent Neural Networks (RNNs) produce state-of-art performance on many machine learning tasks but their demand on resources in terms of memory and computational power are often high. Therefore, there is a great interest in optimizing the…

Recent advancements in deep learning have significantly impacted the field of speech signal processing, particularly in the analysis and manipulation of complex spectrograms. This survey provides a comprehensive overview of the…

Speaker recognition systems based on deep speaker embeddings have achieved significant performance in controlled conditions according to the results obtained for early NIST SRE (Speaker Recognition Evaluation) datasets. From the practical…

Although deep neural networks are successful for many tasks in the speech domain, the high computational and memory costs of deep neural networks make it difficult to directly deploy highperformance Neural Network systems on low-resource…

Supervised training of deep neural nets typically relies on minimizing cross-entropy. However, in many domains, we are interested in performing well on metrics specific to the application. In this paper we propose a direct loss minimization…

Background: Active noise cancellation has been a subject of research for decades. Traditional techniques, like the Fast Fourier Transform, have limitations in certain scenarios. This research explores the use of deep neural networks (DNNs)…

While machine learning techniques are traditionally resource intensive, we are currently witnessing an increased interest in hardware and energy efficient approaches. This need for resource-efficient machine learning is primarily driven by…

The history of deep learning has shown that human-designed problem-specific networks can greatly improve the classification performance of general neural models. In most practical cases, however, choosing the optimal architecture for a…

Deep neural networks (DNNs) are currently widely used for many artificial intelligence (AI) applications including computer vision, speech recognition, and robotics. While DNNs deliver state-of-the-art accuracy on many AI tasks, it comes at…

To reduce random access memory (RAM) requirements and to increase speed of recognition algorithms we consider a weight discretization problem for trained neural networks. We show that an exponential discretization is preferable to a linear…

While binary neural networks (BNNs) offer significant benefits in terms of speed, memory and energy, they encounter substantial accuracy degradation in challenging tasks compared to their real-valued counterparts. Due to the binarization of…

Despite the appeal of deep neural networks that largely replace the traditional handmade filters, they still suffer from isolated cases that cannot be properly handled only by the training of convolutional filters. Abnormal factors,…

We show that selecting a single data type (precision) for all values in Deep Neural Networks, even if that data type is different per layer, amounts to worst case design. Much shorter data types can be used if we target the common case by…

Recurrent Neural Networks (RNNs) produce state-of-art performance on many machine learning tasks but their demand on resources in terms of memory and computational power are often high. Therefore, there is a great interest in optimizing the…

Deep neural networks (DNNs) have been widely applied in diverse applications, but the problems of high latency and energy overhead are inevitable on resource-constrained devices. To address this challenge, most researchers focus on the…

We introduce a method to train Quantized Neural Networks (QNNs) --- neural networks with extremely low precision (e.g., 1-bit) weights and activations, at run-time. At train-time the quantized weights and activations are used for computing…

Neural network quantization is frequently used to optimize model size, latency and power consumption for on-device deployment of neural networks. In many cases, a target bit-width is set for an entire network, meaning every layer get…

Despite noise suppression being a mature area in signal processing, it remains highly dependent on fine tuning of estimator algorithms and parameters. In this paper, we demonstrate a hybrid DSP/deep learning approach to noise suppression. A…

Over the last few years, deep learning has proven to be a great solution to many problems, such as image or text classification. Recently, deep learning-based solutions have outperformed humans on selected benchmark datasets, yielding a…

Deep neural networks generally involve some layers with mil- lions of parameters, making them difficult to be deployed and updated on devices with limited resources such as mobile phones and other smart embedded systems. In this paper, we…