相关论文: Deep Residual Learning for Small-Footprint Keyword…

Dense retrieval is a basic building block of information retrieval applications. One of the main challenges of dense retrieval in real-world settings is the handling of queries containing misspelled words. A popular approach for handling…

Modern approaches for keyword spotting rely on training deep neural networks on large static datasets with i.i.d. distributions. However, the resulting models tend to underperform when presented with changing data regimes in real-life…

Although remarkable progress has been made on single image super-resolution due to the revival of deep convolutional neural networks, deep learning methods are confronted with the challenges of computation and memory consumption in…

Residual network (ResNet) and densely connected network (DenseNet) have significantly improved the training efficiency and performance of deep convolutional neural networks (DCNNs) mainly for object classification tasks. In this paper, we…

Fingerprint recognition has been utilized for cellphone authentication, airport security and beyond. Many different features and algorithms have been proposed to improve fingerprint recognition. In this paper, we propose an end-to-end deep…

Accurate recognition of aviation commands is vital for flight safety and efficiency, as pilots must follow air traffic control instructions precisely. This paper addresses challenges in speech command recognition, such as noisy environments…

We investigate densely connected convolutional networks (DenseNets) and their extension with domain adversarial training for noise robust speech recognition. DenseNets are very deep, compact convolutional neural networks which have…

Due to their ubiquitous and pervasive nature, Wi-Fi networks have the potential to collect large-scale, low-cost, and disaggregate data on multimodal transportation. In this study, we develop a semi-supervised deep residual network (ResNet)…

In this paper, we focus on the task of small-footprint keyword spotting under the far-field scenario. Far-field environments are commonly encountered in real-life speech applications, causing severe degradation of performance due to room…

We present an MatchboxNet - an end-to-end neural network for speech command recognition. MatchboxNet is a deep residual network composed from blocks of 1D time-channel separable convolution, batch-normalization, ReLU and dropout layers.…

In this paper, we propose a fully-neural approach to open-vocabulary keyword spotting, that allows the users to include a customizable voice interface to their device and that does not require task-specific data. We present a keyword…

Despite showing state-of-the-art performance, deep learning for speech recognition remains challenging to deploy in on-device edge scenarios such as mobile and other consumer devices. Recently, there have been greater efforts in the design…

Current state-of-the-art speech recognition systems build on recurrent neural networks for acoustic and/or language modeling, and rely on feature extraction pipelines to extract mel-filterbanks or cepstral coefficients. In this paper we…

Densely connected convolutional networks (DenseNet) behave well in image processing. However, for regression tasks, convolutional DenseNet may lose essential information from independent input features. To tackle this issue, we propose a…

Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition that stills remains an important challenge. Data-driven supervised approaches, including ones based on…

This paper proposes a deep speech enhancement method which exploits the high potential of residual connections in a wide neural network architecture, a topology known as Wide Residual Network. This is supported on single dimensional…

Machine learning has become a major field of research in order to handle more and more complex image detection problems. Among the existing state-of-the-art CNN models, in this paper a region-based, fully convolutional network, for fast and…

Automatic human action recognition is indispensable for almost artificial intelligent systems such as video surveillance, human-computer interfaces, video retrieval, etc. Despite a lot of progress, recognizing actions in an unknown video is…

A keyword spotting (KWS) engine that is continuously running on device is exposed to various speech signals that are usually unseen before. It is a challenging problem to build a small-footprint and high-performing KWS model with robustness…

We explore the use of convolutional neural networks for the semantic classification of remote sensing scenes. Two recently proposed architectures, CaffeNet and GoogLeNet, are adopted, with three different learning modalities. Besides…