检索结果-内蒙古大学图书馆

2017 IEEE 国际医学影像物理和工程大会暨第八届中国医学影像物理学术年会

作者： Sizhu Han Baihan Wang Maoquan Wang Yufei Xie Zhao Lu Yixuan Ku The Key Lab of Brain Functional Genomics MOE &STCSM School of Psychology and Cognitive ScienceEast China Normal University School of Psychology and Cognitive Science East China Normal University School of Computer Science and Software Engineering East China Normal University NYU-ECNU Institute of Brain and Cognitive Science NYU Shanghai

Objective: The storage form of representations in the short-term memory is still controversial. Previous studies provided evidence from behavioral data or univariate activities from local brain areas. Instead, the present study explored this issue by decoding the neural data from the whole brain. Methods: Fifteen participants were recruited to complete a short-term memory task, where they first remembered the direction of a grating, and then after a brief delay（2 s）, they needed to recall the direction by moving and clicking a mouse to match the probe grating with their memorized one. The location of the grating changed from trial to trial. The electroencephalograph（EEG） data were recorded simultaneously, to examine the decoding accuracy of the attended feature（direction） and unattended feature（location）. EEG signals were pre-processed and timefrequency decomposed. Pattern analysis was then conducted on the time-frequency data to predict the feature of direction or location in the memorandum. Results: During the periods of memory encoding and maintenance, the accuracies of predicting the attended feature（direction） and the unattended feature（location） were both 60% ~ 80%, which were significantly higher than the guessing rate（50%） and the predication results using the permutation of the same data. Conclusion: The representation in the visual shortterm memory is stored as a form of binding features in the brain, and the binding between the direction and location may happen in the very early stage of perception that is preattentive.

关键词： visual short-term memory weak-object theory feature binding pattern identification EEG

来源：评论

学校读者我要写书评

暂无评论

AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmark

arXiv

引用

arXiv 2018年

作者： Becker, Sören Vielhaben, Johanna Ackermann, Marcel Müller, Klaus-Robert Lapuschkin, Sebastian Samek, Wojciech Department of Artificial Intelligence Fraunhofer Heinrich-Hertz-Institute Berlin Germany Department of Electrical Engineering and Computer Science Technische Universität Berlin Berlin Germany Department of Brain and Cognitive Engineering Korea University Seoul Korea Republic of Max Planck Institute for Informatics Saarbrücken Germany BIFOLD Berlin Institute for the Foundations of Learning and Data Berlin Germany

Explainable Artificial Intelligence (XAI) is targeted at understanding how models perform feature selection and derive their classification decisions. This paper explores post-hoc explanations for deep neural networks in the audio domain. Notably, we present a novel Open Source audio dataset consisting of 30,000 audio samples of English spoken digits which we use for classification tasks on spoken digits and speakers’ biological sex. We use the popular XAI technique Layer-wise Relevance Propagation (LRP) to identify relevant features for two neural network architectures that process either waveform or spectrogram representations of the data. Based on the relevance scores obtained from LRP, hypotheses about the neural networks’ feature selection are derived and subsequently tested through systematic manipulations of the input data. Further, we take a step beyond visual explanations and introduce audible heatmaps. We demonstrate the superior interpretability of audible explanations over visual ones in a human user study. Copyright © 2018, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

GLEU-guided Multi-Resolution Network for Short Text Conversation

GLEU-guided Multi-Resolution Network for Short Text Conversa...

引用

第十四届全国人机语音通讯学术会议

作者： Xuan Liu Kai Yu Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University

With the recent development of sequence-to-sequence framework,generation approach for short text conversation becomes *** sequence-to-sequence method for short text conversation often suffers from dull response ***-resolution generation approach has been introduced to address this problem by dividing the generation process into two steps:keywords-sequence generation and response ***,this method still tends to generate short and common *** this work,a new multi-resolution generation framework is *** of using the word-level maximum likelihood criterion,we optimize the sequence-level GLEU score of the entire generated keywords-sequence using a policy gradient approach in reinforcement *** show that the proposed approach can generate longer and more diverse ***,it achieves better score in human evaluation.

关键词： short text conversation sequence-to-sequence policy gradient

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion Recognition Based on SVM and GMM-HMM Hybrid System

Speech Emotion Recognition Based on SVM and GMM-HMM Hybrid S...

引用

第十四届全国人机语音通讯学术会议

作者： Kaiyu Shi Xuan Liu Yanmin Qian Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University

Speech emotion recognition is one of the latest challenges in speech processing,we implemented a hybrid system for speech emotion *** methods were proposed,compared and *** first,we utilized GMM-HMM model fed with MFCC feature to exploit the dynamics of emotional *** a balanced SVM classifier was applied on the static LLD *** order to take advantage of generative model and discriminate model,these two methods were combined by taking the probability representation of the GMM-HMM model as the additional features for the SVM *** hybrid system makes full use of both MFCC feature and LLD feature,the performance of the hybrid system also proves the effectiveness of our proposed system.

关键词： speech emotion recognition SVM GMMHMM hybrid system

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition Using Support Vector Machine and Deep Neural Network

Emotion Recognition Using Support Vector Machine and Deep Ne...

引用

第十四届全国人机语音通讯学术会议

作者： Chen Ruinian Zhou Ying Qian Yanmin Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University

We propose a classification system which is a combination of three subsystem to solve the speech emotion recognition *** first subsystem utilizes support vector machines(SVMs) to classify the features *** second subsystem utilizes deep neural networks(DNNs) to classify the features *** the third subsystem,we utilize DNNs to extract high level features from raw data and show that they are effective for speech emotion *** first produce an emotion state probability distribution for each speech segment using DNNs,then we construct utterance-level features from segment-level probability *** utterance level features are fed into an SVM to identify utterance-level *** experimental results show that all the subsystems are outperform the HMM baseline system,and the combined system get the best result on F-score.

关键词： Emotion recognition Deep neural networks Support vector machine

来源：评论

学校读者我要写书评

暂无评论

Fusion Model for Speech Emotion Recognition with Low Level Descriptor Features

Fusion Model for Speech Emotion Recognition with Low Level D...

引用

第十四届全国人机语音通讯学术会议

作者： Cheng Chang Huifeng Zhang Zhangxuan Gu Yanmin Qian Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University

Speech emotion recognition is one of the most challenging speech processing tasks,with many applications in the field of Human-Machine Interaction(HMI).Traditional works have been using Gaussian Mixture Models(GMM) for *** recent researches,Deep Neural Networks(DNN) have shown strong ability in feature learning and modeling in many *** this paper,we present to utilize the DNN to learn extra features from Low Level Descriptor(LLD) features for other classifiers,and propose a decision-level fusion model for speech emotion *** carry out experiments and evaluations on a public German corpus called FAU-AIBO with five *** our experimental results using LLD features demonstrate that our proposed approach improves the recognition performance on unweighted results and outperforms the baseline using GMM significantly.

关键词： speech emotion recognition deep neural network low level descriptor fusion

来源：评论

学校读者我要写书评

暂无评论

SMALL-FOOTPRINT CONVOLUTIONAL NEURAL NETWORK FOR SPOOFING DETECTION

SMALL-FOOTPRINT CONVOLUTIONAL NEURAL NETWORK FOR SPOOFING DE...

引用

International Joint Conference on Neural Networks

作者： Heinrich Dinkel Yanmin Qian Kai Yu Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University

ISBN: (纸本)9781509061839

Albeit recent progress in speaker verification engendered powerful models, malicious attacks in the form of spoofed speech, are generally not coped with. In previous attempts, deep neural networks were used to extract high dimensional features which were later classified using an independent classifier. Even though the results of this approach are promising, this architecture's disadvantage is it's complexity of optimizing both, neural network and back-end classifier. In this paper we present a simplified neural network approach to address this problem based on the convolutional neural network architecture. Our model concatenates the output of all abstract convolutional representations within the network into a single high-dimensional vector. By preserving all the information within the network, the networks generalization capabilities are greatly enhanced, resulting in an favorable error rate of 5.4% on the S10 condition. Scores are frame wise obtained by directly extracting the posteriors from the output neurons and further reduced to an utterance score by the use of variance reduction. We show that by using variance posterior score reduction, large performance gains can be achieved. This model outperforms standard feature extracting neural network approaches, in addition on being more versatile, robust and faster to train. Our best model achieves an error rate of 0.7% on the ASVspoof corpus, utilizing common PLP features. It significantly outperforms conventional feature extraction neural networks, while only having 100k parameters.

关键词： Neural network Error analysis Feature extraction speaker recognition Classifiers Information Network neural net architecture

来源：评论

学校读者我要写书评

暂无评论

Understanding patch-based learning by explaining predictions

arXiv

引用

arXiv 2018年

作者： Anders, Christopher Montavon, Grégoire Samek, Wojciech Müller, Klaus-Robert Dept. of Computer Science Technische Universität Berlin Berlin10587 Germany Dept. of Video Coding & Analytics Fraunhofer Heinrich Hertz Institute Berlin10587 Germany Dept. of Brain & Cognitive Engineering Korea University Seoul136-713 Korea Republic of Max Planck Institute for Informatics Saarbrücken66123 Germany

Deep networks are able to learn highly predictive models of video data. Due to video length, a common strategy is to train them on small video snippets. We apply the deep Taylor / LRP technique to understand the deep network's classification decisions, and identify a "border effect": a tendency of the classifier to look mainly at the bordering frames of the input. This effect relates to the step size used to build the video snippet, which we can then tune in order to improve the classifier's accuracy without retraining the model. To our knowledge, this is the the first work to apply the deep Taylor / LRP technique on any video analyzing neural network. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Encoder-decoder with focus-mechanism for sequence labelling based spoken language understanding

Encoder-decoder with focus-mechanism for sequence labelling ...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Su Zhu Kai Yu Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University China

ISBN: (纸本)9781509041183

This paper investigates the framework of encoder-decoder with attention for sequence labelling based spoken language understanding. We introduce Bidirectional Long Short Term Memory - Long Short Term Memory networks (BLSTM-LSTM) as the encoder-decoder model to fully utilize the power of deep learning. In the sequence labelling task, the input and output sequences are aligned word by word, while the attention mechanism cannot provide the exact alignment. To address this limitation, we propose a novel focus mechanism for encoder-decoder framework. Experiments on the standard ATIS dataset showed that BLSTM-LSTM with focus mechanism defined the new state-of-the-art by outperforming standard BLSTM and attention based encoder-decoder. Further experiments also show that the proposed model is more robust to speech recognition errors.

关键词： Spoken language understanding encoder-decoder focus-mechanism robustness spoken language understanding Word Packaging Short-Term Memory Robustness Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Author Correction: Aplp1 interacts with Lag3 to facilitate transmission of pathologic α-synuclein

引用

Nature communications 2024年第1期15卷 6413页

作者： Xiaobo Mao Hao Gu Donghoon Kim Yasuyoshi Kimura Ning Wang Enquan Xu Ramhari Kumbhar Xiaotian Ming Haibo Wang Chan Chen Shengnan Zhang Chunyu Jia Yuqing Liu Hetao Bian Senthilkumar S Karuppagounder Fatih Akkentli Qi Chen Longgang Jia Heehong Hwang Su Hyun Lee Xiyu Ke Michael Chang Amanda Li Jun Yang Cyrus Rastegar Manjari Sriparna Preston Ge Saurav Brahmachari Sangjune Kim Shu Zhang Yasushi Shimoda Martina Saar Haiqing Liu Sin Ho Kweon Mingyao Ying Creg J Workman Dario A A Vignali Ulrike C Muller Cong Liu Han Seok Ko Valina L Dawson Ted M Dawson Neuroregeneration and Stem Cell Programs Institute for Cell Engineering Johns Hopkins University School of Medicine Baltimore MD 21205 USA. xmao4@jhmi.edu. Department of Neurology Johns Hopkins University School of Medicine Baltimore MD 21205 USA. xmao4@jhmi.edu. Adrienne Helis Malvin Medical Research Foundation New Orleans LA 70130-2685 USA. xmao4@jhmi.edu. Neuroregeneration and Stem Cell Programs Institute for Cell Engineering Johns Hopkins University School of Medicine Baltimore MD 21205 USA. Department of Neurology Johns Hopkins University School of Medicine Baltimore MD 21205 USA. Department of Neurology Nanjing Brain Hospital Nanjing Jiangsu 210029 PR China. Medical College Yangzhou University Yangzhou Jiangsu 225001 PR China. Department of Pharmacology College of Medicine Dong-A University 32 Daesin Gongwwon-ro Seo-gu Busan 49201 Republic of Korea. Adrienne Helis Malvin Medical Research Foundation New Orleans LA 70130-2685 USA. Department of Anesthesiology West China Hospital Sichuan University. The Research Units of West China (2018RU012)-Chinese Academy of Medical Sciences West China Hospital Sichuan University Chengdu Sichuan 610041 PR China. Interdisciplinary Research Center on Biology and Chemistry Shanghai Institute of Organic Chemistry Chinese Academy of Sciences 26 Qiuyue Road Shanghai 201210 China. University of the Chinese Academy of Sciences 19 A Yuquan Road Shijingshan District Beijing 100049 China. Institute for NanoBioTechnology Johns Hopkins University Baltimore MD 21218 USA. Department of Materials Science and Engineering Whiting School of Engineering Johns Hopkins University Baltimore MD 21218 USA. Department of Brain and Cognitive Sciences Massachusetts Institute of Technology Cambridge MA 02139 USA. Picower Institute for Learning and Memory Cambridge MA 02139 USA. Harvard-MIT MD/PhD Program Harvard Medical School Boston MA 02115 USA. Department of Biological Science and Biotechnology Chungbuk Nati

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：