Related papers: BiFSMN: Binary Neural Network for Keyword Spotting

This paper addresses the challenges of mining latent patterns and modeling contextual dependencies in complex sequence data. A sequence pattern mining algorithm is proposed by integrating Bidirectional Long Short-Term Memory (BiLSTM) with a…

Keyword spotting (KWS) is an important technique for speech applications, which enables users to activate devices by speaking a keyword phrase. Although a phoneme classifier can be used for KWS, exploiting a large amount of transcribed data…

Keyword spotting (KWS) is experiencing an upswing due to the pervasiveness of small electronic devices that allow interaction with them via speech. Often, KWS systems are speaker-independent, which means that any person --user or not--…

Despite their great performance over the years, handcrafted speech features are not necessarily optimal for any particular speech application. Consequently, with greater or lesser success, optimal filterbank learning has been studied for…

Model binarization is an effective method of compressing neural networks and accelerating their inference process. However, a significant performance gap still exists between the 1-bit model and the 32-bit one. The empirical study shows…

The performance and ease of use of deep learning-based binary classifiers have improved significantly in recent years. This has opened up the potential for automating critical inspection tasks, which have traditionally only been trusted to…

Quantizing weights and activations of deep neural networks is essential for deploying them in resource-constrained devices, or cloud platforms for at-scale services. While binarization is a special case of quantization, this extreme case…

There is a need for fast adaptation in spike sorting algorithms to implement brain-machine interface (BMIs) in different applications. Learning and adapting the functionality of the sorting process in real-time can significantly improve the…

High-definition (HD) cameras for surveillance and road traffic have experienced tremendous growth, demanding intensive computation resources for real-time analytics. Recently, offloading frames from the front-end device to the back-end edge…

Deep convolutional neural networks (DCNNs) have recently demonstrated high-quality results in single-image super-resolution (SR). DCNNs often suffer from over-parametrization and large amounts of redundancy, which results in inefficient…

Successful motor-imagery brain-computer interface (MI-BCI) algorithms either extract a large number of handcrafted features and train a classifier, or combine feature extraction and classification within deep convolutional neural networks…

Deep Neural Networks (DNN) have been successful in en- hancing noisy speech signals. Enhancement is achieved by learning a nonlinear mapping function from the features of the corrupted speech signal to that of the reference clean speech…

A key enabler of deploying convolutional neural networks on resource-constrained embedded systems is the binary neural network (BNN). BNNs save on memory and simplify computation by binarizing both features and weights. Unfortunately,…

Developing resource allocation algorithms with strong real-time and high efficiency has been an imperative topic in wireless networks. Conventional optimization-based iterative resource allocation algorithms often suffer from slow…

Biclustering is a powerful unsupervised learning technique for simultaneously identifying coherent subsets of rows and columns in a data matrix, thus revealing local patterns that may not be apparent in global analyses. However, most…

In this paper, we propose a multilingual query-by-example keyword spotting (KWS) system based on a residual neural network. The model is trained as a classifier on a multilingual keyword dataset extracted from Common Voice sentences and…

Spiking neural network (SNN) is a brain-inspired model which has more spatio-temporal information processing capacity and computational energy efficiency. However, with the increasing depth of SNNs, the memory problem caused by the weights…

The spiking neural network (SNN) computes and communicates information through discrete binary events. It is considered more biologically plausible and more energy-efficient than artificial neural networks (ANN) in emerging neuromorphic…

Many approaches for verifying input-output properties of neural networks have been proposed recently. However, existing algorithms do not scale well to large networks. Recent work in the field of model compression studied binarized neural…

One of the most exciting applications of Spin Torque Magnetoresistive Random Access Memory (ST-MRAM) is the in-memory implementation of deep neural networks, which could allow improving the energy efficiency of Artificial Intelligence by…