检索结果-内蒙古大学图书馆

IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

作者： Meng, Zhong Li, Jinyu Gaur, Yashesh Gong, Yifan Microsoft Corp Redmond WA 98052 USA

ISBN: (纸本)9781728103068

Teacher-student (T/S) has shown to be effective for domain adaptation of deep neural network acoustic models in hybrid speech recognition systems. In this work, we extend the T/S learning to large-scale unsupervised domain adaptation of an attention-based end-to-end (E2E) model through two levels of knowledge transfer: teacher's token posteriors as soft labels and one-best predictions as decoder guidance. To further improve T/S learning with the help of ground-truth labels, we propose adaptive T/S (AT/S) learning. Instead of conditionally choosing from either the teacher's soft token posteriors or the one-hot ground-truth label, in AT/S, the student always learns from both the teacher and the ground truth with a pair of adaptive weights assigned to the soft and one-hot labels quantifying the confidence on each of the knowledge sources. The confidence scores are dynamically estimated at each decoder step as a function of the soft and one-hot labels. With 3400 hours parallel close-talk and far-field Microsoft Cortana data for domain adaptation, T/S and AT/S achieves 6.3% and 10.3% relative word error rate improvement over a strong E2E model trained with the same amount of far-field data.

关键词： domain adaptation teacher-student learning end-to-end encoder-decoder speech recognition

来源：评论

学校读者我要写书评

暂无评论

Pretraining by Backtranslation for End-to-end ASR in Low-Resource Settings 20

Pretraining by Backtranslation for End-to-end ASR in Low-Res...

引用

Interspeech Conference

作者： Wiesner, Matthew Renduchintala, Adithya Watanabe, Shinji Liu, Chunxi Dehak, Najim Khudanpur, Sanjeev Johns Hopkins Univ Ctr Language & Speech Proc Baltimore MD 21218 USA Johns Hopkins Univ Human Language Technol Ctr Excellence Baltimore MD 21218 USA

We explore training attention-based encoder-decoder ASR in low-resource settings. These models perform poorly when trained on small amounts of transcribed speech, in part because they depend on having sufficient target-side text to train the attention and decoder networks. In this paper we address this shortcoming by pretraining our network parameters using only text-based data and transcribed speech from other languages. We analyze the relative contributions of both sources of data. Across 3 test languages, our text-based approach resulted in a 20% average relative improvement over a text-based augmentation technique without pretraining. Using transcribed speech from nearby languages gives a further 20-30% relative reduction in character error rate.

关键词： Multi-modal data augmentation pretraining multilingual ASR encoder-decoder low-resource

来源：评论

学校读者我要写书评

暂无评论

A novel image-dehazing network with a parallel attention block

引用

PATTERN RECOGNITION 2020年第0期102卷 107255-000页

作者： Yin, Shibai Wang, Yibin Yang, Yee-Hong Southwestern Univ Finance & Econ Dept Econ Informat Engn Chengdu 611130 Sichuan Peoples R China Sichuan Normal Univ Dept Engn Chengdu 610066 Sichuan Peoples R China Univ Alberta Dept Comp Sci Edmonton AB T6G 2E8 Canada

Image dehazing is a very important pre-processing step to many computer vision tasks such as object recognition and tracking. However, it is a challenging problem because the physical parameters of imaging, e.g. the depth information of scene pixels and the attenuation model, are usually unknown. Based on a physical model, different methods have been proposed to recover these parameters. Existing convolutional neural networks (CNNs) based methods try to solve the image dehazing problem using an end-to-end network to learn a direct mapping between a hazy image and its corresponding clear image. But the representational ability, spatial variant ability and dehazing capability of these network models are hindered by treating all the spatial and channel-wise features indiscriminately. Hence, we propose an end-to-end dehazing network with a parallel spatial/channel-wise attention block for capturing more informative spatial and channel-wise features respectively. Specifically, based on the encoder-decoder framework with a pyramid pooling operation, a novel parallel spatial/channel-wise attention block is proposed and applied to the end of the encoder for guiding the decoder to reconstruct better clear images. In the spatial/channel-wise attention block, the spatial attention module and the channel-wise attention module are connected in parallel, where the spatial attention module highlights important spatial positions of features. Meanwhile, the channel-wise module exploits inter-dependencies among the channel-wise features. Extensive experiments demonstrate that our network with a parallel spatial/channel-wise attention block can achieve better accuracy and visual results over state-of-the-art methods. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Image dehazing Spatial attention mechanism Channel-wise attention mechanism encoder-decoder CNN

来源：评论

学校读者我要写书评

暂无评论

PREDICTING HUMAN GRASP LOCATIONS ON CUP HANDLES BY USING DEEP NEURAL NETWORKS TO INFER HEAT SIGNATURES FROM DEPTH DATA

PREDICTING HUMAN GRASP LOCATIONS ON CUP HANDLES BY USING DEE...

引用

IEEE International Conference on Multimedia and Expo (IEEE ICME)

作者： Jiang, Yijun Banerjee, Sean Banerjee, Natasha Kholgade Clarkson Univ Potsdam NY 13699 USA

ISBN: (纸本)9781538692141

In automated assisted living where a robot assists a human to interact with physical objects, an important challenge is for a robot to understand where humans are likely to grasp objects, so that the robot can present the object to a user in the most tenable configuration. In this paper, we present an approach that uses encoder-decoder convolutional neural networks (CNNs) to predict human grasp location on cup handles. The primary challenge addressed by our work is that object occlusion induced by the human hand prevents direct imaging of grasp location. Our approach uses the insight that once the object is released, the hand leaves a heat signature on the object surface due to the temperature differences between the human body and the ambient environment. Our CNNs learn a mapping between images obtained from traditional depth sensors as input and heat signatures of grasp locations imaged using a thermal camera as output. Given the depth image of a novel cup, our approach uses the trained network to predict the grasp probability distribution over the cup. Using a leave-one-cup-out approach, we obtain a mean absolute pixel-wise prediction error of 5.67 on 17 cups imaged from 7 orientations.

关键词： human grasp thermal maps depth encoder-decoder neural network grasp prediction

来源：评论

学校读者我要写书评

暂无评论

End-to-End Image Dehazing via Dual Principles of Discriminativeness 11

End-to-End Image Dehazing via Dual Principles of Discriminat...

引用

11th International Conference on Digital Image Processing (ICDIP)

作者： Ye, Lu-Yue Liu, Yuan-Yuan Shao, Wen-Ze Wang, Li-Qian Bao, Bing-Kun Li, Hai-Bo Nanjing Univ Posts & Telecommun Coll Telecommun & Informat Engn 66 Xinmofan Rd Nanjing 210003 Peoples R China

ISBN: (数字)9781510630765

ISBN: (纸本)9781510630765

This work addresses the problem of single image dehazing particularly towards the goal of better visibility restoration. Athough extensive studies have been performed, almost all of them are heavily built on the atmospheric scattering model. What is worse, they usually fail to restore the visibility of dense hazy images convincingly. Inspired by the potentials of deep learning, a new end-to-end approach is presented to restore a clear image directly from a hazy image, while with an emphasis on the real-world weather conditions. In specific, an encoder-decoder is exploited as a generator for restoring the dehazed image in an attempt of preserve more image details. Interestingly, it is further found that the performance of the encoder-decoder can be largely boosted via our advocated dual principles of discriminativeness in this paper. On the one hand, the dark channel is re-explored in our framework resulting in a discriminative prior formulated specifically for the dehazing problem. On the other hand, a critic is incorporated for adversarial training against the autoencoding-based generator, implemented via the Wasserstein GAN (generative adverarial networks) regularized by the Liptchitiz penalty. The proposed approach is trained on a synthetic dataset of hazy images, while evaluated on both synthetic and real hazy images. The objective evaluation has shown that the proposed approach performs competitively with the state-of-the-art approaches, but outperforms them in terms of the visibility restoration especially in the scenarios of dense haze.

关键词： Dehazing dark channel generative adversarial networks encoder-decoder visibility restoration

来源：评论

学校读者我要写书评

暂无评论

Estimation of 2D Velocity Model using Acoustic Signals and Convolutional Neural Networks 26

Estimation of 2D Velocity Model using Acoustic Signals and C...

引用

IEEE 26th International Conference on Electronics, Electrical Engineering and Computing (INTERCON)

作者： Apolinario, Marco Paul E. Huaman Bustamante, Samuel G. Morales, Giorgio Diaz, Daniel Natl Univ Engn Natl Inst Res & Training Telecommun INICTEL UNI Lima Peru

ISBN: (纸本)9781728136462

The parameters estimation of a system using indirect measurements over the same system is a problem that occurs in many fields of engineering, known as the inverse problem. It also happens in the field of underwater acoustic, especially in mediums that are not transparent enough. In those cases, shape identification of objects using only acoustic signals is a challenge because it is carried out with information of echoes that are produced by objects with different densities from that of the medium. In general, these echoes are difficult to understand since their information is usually noisy and redundant. In this paper, we propose a model of convolutional neural network with an encoder-decoder configuration to estimate both localization and shape of objects, which produce reflected signals. This model allows us to obtain a 2D velocity model. The model was trained with data generated by the finite-difference method, and it achieved a value of 98.58% in the intersection over union metric 75.88% in precision and 64.69% in sensitivity.

关键词： Deep Learning Acoustic Wave Equation Finite-Difference Method encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Deep Neural Networks for Semantic Segmentation of Prostate in T2W MRI

引用

SENSORS 2020年第11期20卷 3183.-3183.页

作者： Khan, Zia Yahya, Norashikin Alsaih, Khaled Ali, Syed Saad Azhar Meriaudeau, Fabrice Univ Teknol PETRONAS Ctr Intelligent Signal & Imaging Res CISIR Dept Elect & Elect Engn Seri Iskandar 32610 Perak Malaysia Univ Burgundy ImViA ITFIM F-21078 Dijon France

In this paper, we present an evaluation of four encoder-decoder CNNs in the segmentation of the prostate gland in T2W magnetic resonance imaging (MRI) image. The four selected CNNs are FCN, SegNet, U-Net, and DeepLabV3+, which was originally proposed for the segmentation of road scene, biomedical, and natural images. Segmentation of prostate in T2W MRI images is an important step in the automatic diagnosis of prostate cancer to enable better lesion detection and staging of prostate cancer. Therefore, many research efforts have been conducted to improve the segmentation of the prostate gland in MRI images. The main challenges of prostate gland segmentation are blurry prostate boundary and variability in prostate anatomical structure. In this work, we investigated the performance of encoder-decoder CNNs for segmentation of prostate gland in T2W MRI. Image pre-processing techniques including image resizing, center-cropping and intensity normalization are applied to address the issues of inter-patient and inter-scanner variability as well as the issue of dominating background pixels over prostate pixels. In addition, to enrich the network with more data, to increase data variation, and to improve its accuracy, patch extraction and data augmentation are applied prior to training the networks. Furthermore, class weight balancing is used to avoid having biased networks since the number of background pixels is much higher than the prostate pixels. The class imbalance problem is solved by utilizing weighted cross-entropy loss function during the training of the CNN model. The performance of the CNNs is evaluated in terms of the Dice similarity coefficient (DSC) and our experimental results show that patch-wise DeepLabV3+ gives the best performance with DSC equal to 92.8%. This value is the highest DSC score compared to the FCN, SegNet, and U-Net that also competed the recently published state-of-the-art method of prostate segmentation.

关键词： encoder-decoder CNNs DNN FCN SegNet U-Net DeepLabV3+

来源：评论

学校读者我要写书评

暂无评论

Trace2trace-A Feasibility Study on Neural Machine Translation Applied to Human Motion Trajectories

引用

SENSORS 2020年第12期20卷 3503.-3503.页

作者： Crivellari, Alessandro Beinat, Euro Univ Salzburg Dept Geoinformat Z GIS A-5020 Salzburg Austria

Neural machine translation is a prominent field in the computational linguistics domain. By leveraging the recent developments of deep learning, it gave birth to powerful algorithms for translating text from one language to another. This study aims to assess the feasibility of transferring the neural machine translation approach into a completely different context, namely human mobility and trajectory analysis. Building a conceptual parallelism between sentences (sequences of words) and motion traces (sequences of locations), we aspire to translate individual trajectories generated by a certain category of users into the corresponding mobility traces potentially generated by a different category of users. The experiment is inserted in the background of tourist mobility analysis, with the goal of translating the motion behavior of tourists belonging to a specific nationality into the motion behavior of tourists belonging to a different nationality. The model adopted is based on the seq2seq approach and consists of an encoder-decoder architecture based on long short-term memory (LSTM) neural networks and neural embeddings. The encoder turns an input location sequence into a corresponding hidden vector;the decoder reverses the process, turning the vector into an output location sequence. The proposed framework, tested on a real-world large-scale dataset, explores an effective attempt of motion transformation between different entities, arising as a potentially powerful source of mobility information disclosure, especially in the context of crowd management and smart city services.

关键词： seq2seq encoder-decoder neural networks LSTM trajectories motion behavior smart tourism

来源：评论

学校读者我要写书评

暂无评论

Automatic Tongue Image Segmentation For Real-Time Remote Diagnosis

Automatic Tongue Image Segmentation For Real-Time Remote Dia...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Li, Xinlei Yang, Dawei Wang, Yan Yang, Shuai Qi, Lizhe Li, Fufeng Gan, Zhongxue Zhang, Wenqiang Fudan Univ Acad Engn & Technol Shanghai Peoples R China Shanghai Univ TCM Lab TCM Four Proc Shanghai Peoples R China

ISBN: (纸本)9781728118673

Tongue diagnosis, one of the essential diagnostic methods of Traditional Chinese Medicine (TCM), is considered an ideal candidate for remote diagnosis methods because of its convenience and noninvasiveness. However, the trade-off between accuracy and efficiency and the variation of tongue images pose great challenges in real-time tongue image segmentation. To remedy these problems, in this paper, a light weight architecture based on the encoder-decoder structure is proposed. The tongue image feature extraction (TIFE) module is designed to generate features with larger receptive fields without sacrificing spatial resolution. The context module is used to increase the performance by aggregating multi-scale contextual information. The decoder is designed as a simple yet efficient feature upsampling module to fuse different depth features and refine the segmentation results along tongue boundaries. The loss module is proposed to deal with misclassifications causing by class imbalance. A new tongue image dataset (FDU/SHUTCM) is constructed for model training and testing, which contains 5,600 tongue images and their corresponding high quality masks. We demonstrate the effectiveness of the proposed model on BioHit, PolyU/HIT, and our datasets, achieving the performance of 99.15%, 95.69%, and 99.03% IoU accuracy, respectively. Segmentation of a 513x513 image takes 165 ms on CPU.

关键词： Tongue diagnosis Remote Diagnosis Real-time Segmentation Light Weight Networks encoder-decoder Dilated Convolutions Multi-scale Context Aggregation Class Imbalance

来源：评论

学校读者我要写书评

暂无评论

ADDITIONAL SHARED decoder ON SIAMESE MULTI-VIEW encoderS FOR LEARNING ACOUSTIC WORD EMBEDDINGS

ADDITIONAL SHARED DECODER ON SIAMESE MULTI-VIEW ENCODERS FOR...

引用

IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

作者： Jung, Myunghun Lim, Hyungjun Goo, Jahyun Jung, Youngmoon Kim, Hoirin Korea Adv Inst Sci & Technol Sch Elect Engn Daejeon South Korea

ISBN: (纸本)9781728103068

Acoustic word embeddings - fixed-dimensional vector representations of arbitrary-length words - have attracted increasing interest in query-by-example spoken term detection. Recently, on the fact that the orthography of text labels partly reflects the phonetic similarity between the words' pronunciation, a multi-view approach has been introduced that jointly learns acoustic and text embeddings. It showed that it is possible to learn discriminative embeddings by designing the objective which takes text labels as well as word segments. In this paper, we propose a network architecture that expands the multi-view approach by combining the Siamese multiview encoders with a shared decoder network to maximize the effect of the relationship between acoustic and text embeddings in embedding space. Discriminatively trained with multi-view triplet loss and decoding loss, our proposed approach achieves better performance on acoustic word discrimination task with the WSJ dataset, resulting in 11.1% relative improvement in average precision. We also present experimental results on cross-view word discrimination and word level speech recognition tasks.

关键词： acoustic word embedding query-by-example spoken term detection multi-view learning Siamese network encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：