相关论文: ASR Performance Prediction on Unseen Broadcast Pro…

Recent advances in hardware and big data acquisition have accelerated the development of deep learning techniques. For an extended period of time, increasing the model complexity has led to performance improvements for various tasks.…

Alongside acoustic information, linguistic features based on speech transcripts have been proven useful in Speech Emotion Recognition (SER). However, due to the scarcity of emotion labelled data and the difficulty of recognizing emotional…

We propose automatic speech recognition (ASR) models inspired by echo state network (ESN), in which a subset of recurrent neural networks (RNN) layers in the models are randomly initialized and untrained. Our study focuses on RNN-T and…

Sentiment analysis is known as one of the most crucial tasks in the field of natural language processing and Convolutional Neural Network (CNN) is one of those prominent models that is commonly used for this aim. Although convolutional…

A paper published in the CVPR 2019 conference outlines a new technique called 'kervolution' used in a new type of augmented convolutional neural network (CNN) called a 'kervolutional neural network' (KNN). The paper asserts that KNNs…

Voice-enabled commercial products are ubiquitous, typically enabled by lightweight on-device keyword spotting (KWS) and full automatic speech recognition (ASR) in the cloud. ASR systems require significant computational resources in…

Recognizer Output Voting Error Reduction (ROVER) has been widely used for system combination in automatic speech recognition (ASR). In order to select the most appropriate words to insert at each position in the output transcriptions, some…

Convolutional neural networks (CNNs) have achieved high performance in synthetic aperture radar (SAR) automatic target recognition (ATR). However, the performance of CNNs depends heavily on a large amount of training data. The insufficiency…

Benefit from large-scale training datasets, deep Convolutional Neural Networks(CNNs) have achieved impressive results in face recognition(FR). However, tremendous scale of datasets inevitably lead to noisy data, which obviously reduce the…

Recent saliency models extensively explore to incorporate multi-scale contextual information from Convolutional Neural Networks (CNNs). Besides direct fusion strategies, many approaches introduce message-passing to enhance CNN features or…

How to model a pair of sentences is a critical issue in many NLP tasks such as answer selection (AS), paraphrase identification (PI) and textual entailment (TE). Most prior work (i) deals with one individual task by fine-tuning a specific…

Convolutional neural network (CNN) is widely used in computer vision applications. In the networks that deal with images, CNNs are the most time-consuming layer of the networks. Usually, the solution to address the computation cost is to…

Learning powerful feature representations for image retrieval has always been a challenging task in the field of remote sensing. Traditional methods focus on extracting low-level hand-crafted features which are not only time-consuming but…

Despite the effectiveness of Convolutional Neural Networks (CNNs) for image classification, our understanding of the relationship between shape of convolution kernels and learned representations is limited. In this work, we explore and…

This paper proposes a self-supervised learning approach for video features that results in significantly improved performance on downstream tasks (such as video classification, captioning and segmentation) compared to existing methods. Our…

Machine learning algorithms have recently been considered for many tasks in the field of wireless communications. Previously, we have proposed the use of a deep fully convolutional neural network (CNN) for receiver processing and shown it…

In machine learning for fluid mechanics, fully-connected neural network (FNN) only uses the local features for modelling, while the convolutional neural network (CNN) cannot be applied to data on structured/unstructured mesh. In order to…

Error correction techniques remain effective to refine outputs from automatic speech recognition (ASR) models. Existing end-to-end error correction methods based on an encoder-decoder architecture process all tokens in the decoding phase,…

For about 10 years, detecting the presence of a secret message hidden in an image was performed with an Ensemble Classifier trained with Rich features. In recent years, studies such as Xu et al. have indicated that well-designed…

Current research in Computer Vision has shown that Convolutional Neural Networks (CNN) give state-of-the-art performance in many classification tasks and Computer Vision problems. The embedding of CNN, which is the internal representation…