检索结果-内蒙古大学图书馆

11th International Conference on Robotics, Vision, Signal processing and Power Applications, RoViSP 2021

作者： Malik, Najeeb Ur Rehman Abu Bakar, Syed Abdul Rahman Sheikh, Usman Ullah Computer Vision Video and Image Processing Lab ECE Department Universiti Teknologi Malaysia Johor Malaysia

ISBN: (纸本)9789811681288

Human action recognition is one of the trending research topics in the field of computer vision. Human-computer interaction and video monitoring are broad applications that aid in the understanding of human action in a video. The problem with action recognition algorithms such as 3D CNN, Two-stream network, and CNN-LSTM is that they have highly complex models including a lot of parameters resulting in difficulty while training them. Such models require high configuration machines for real-time human action recognition. Therefore, present research proposes the use of 2D skeleton features along with a KNN classifier based HAR system to overcome the aforementioned problems of complexity and response time. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of ASR Methods for Speech Deepfake Detection

Comparative Analysis of ASR Methods for Speech Deepfake Dete...

引用

Asilomar Conference on Signals, Systems & Computers

作者： Davide Salvi Amit Kumar Singh Yadav Kratika Bhagtani Viola Negronil Paolo Bestagini Edward J. Delp Image and Sound Processing Lab (ISPL) Politecnico di Milano Milano Italy Video and Image Processing Lab (VIPER) Purdue University West Lafayette Indiana USA

ISBN: (数字)9798350354058

ISBN: (纸本)9798350354065

Recent techniques for speech deepfake detection often rely on pre-trained self-supervised models. These systems, initially developed for Automatic Speech Recognition (ASR), have proved their ability to offer a meaningful representation of speech signals, which can benefit various tasks, including deepfake detection. In this context, pre-trained models serve as feature extractors and are used to extract embeddings from input speech, which are then fed to a binary speech deepfake detector. The remarkable accuracy achieved through this approach underscores a potential relationship between ASR and speech deepfake detection. However, this connection is not yet entirely clear, and we do not know whether improved performance in ASR corresponds to higher speech deepfake detection capabilities. In this paper, we address this question through a systematic analysis. We consider two different pre-trained self-supervised ASR models, Whisper and Wav2Vec 2.0, and adapt them for the speech deepfake detection task. These models have been released in multiple versions, with increasing number of parameters and enhanced ASR performance. We investigate whether performance improvements in ASR correlate with improvements in speech deepfake detection. Our results provide insights into the relationship between these two tasks and offer valuable guidance for the development of more effective speech deepfake detectors.

关键词： Deepfakes Adaptation models Accuracy Systematics Forensics Detectors Speech enhancement Feature extraction Market research Context modeling

来源：评论

学校读者我要写书评

暂无评论

Transformer Ensemble for Synthesized Speech Detection

Transformer Ensemble for Synthesized Speech Detection

引用

Asilomar Conference on Signals, Systems & Computers

作者： Emily R. Bartusiak Kratika Bhagtani Amit Kumar Singh Yadav Edward J. Delp Video and Image Processing Lab School of Electrical and Computer Engineering Purdue University West Lafayette IN

As voice synthesis systems and deep learning tools continue to improve, so does the possibility that synthesized speech can be used for nefarious purposes. Methods that determine if audio signals contain synthesized or authentic speech are needed. In this paper, we investigate three transformers to detect synthesized speech: Compact Convolutional Transformer (CCT), Patchout faSt Spectrogram Transformer (PaSST), and Self-Supervised Audio Spectrogram Transformer (SSAST). We show that each transformer independently detects synthesized speech well. Then, we propose an ensemble of transformers that can provide even better performance. Finally, we explore how much of an audio signal is needed for high synthesized speech detection. Evaluated on the ASVspoof2019 dataset, we demonstrate that our transformer ensemble detects synthesized speech from shorter segments of audio signals, even on a highly imbalanced dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CHASE: Robust Visual Tracking via Cell-Level Differentiable Neural Architecture Search 32

CHASE: Robust Visual Tracking via Cell-Level Differentiable ...

引用

32nd British Machine Vision Conference, BMVC 2021

作者： Marvasti-Zadeh, Seyed Mojtaba Khaghani, Javad Cheng, Li Ghanei-Yakhdan, Hossein Kasaei, Shohreh Vision and Learning Lab University of Alberta Edmonton Canada Digital Image & Video Processing Lab Yazd University Yazd Iran Image Processing Lab Sharif University of Technology Tehran Iran

A strong visual object tracker nowadays relies on its well-crafted modules, which typically consist of manually-designed network architectures to deliver high-quality tracking results. Not surprisingly, the manual design process becomes a particularly challenging barrier, as it demands sufficient prior experience, enormous effort, intuition, and perhaps some good luck. Meanwhile, neural architecture search has gaining grounds in practical applications as a promising method in tackling the issue of automated search of feasible network structures. In this work, we propose a novel cell-level differentiable architecture search mechanism with early stopping to automate the network design of the tracking module, aiming to adapt backbone features to the objective of Siamese tracking networks during offline training. Besides, the proposed early stopping strategy avoids over-fitting and performance collapse problems leading to generalization improvement. The proposed approach is simple, efficient, and with no need to stack a series of modules to construct a network. Our approach is easy to be incorporated into existing trackers, which is empirically validated using different differentiable architecture search-based methods and tracking objectives. Extensive experimental evaluations demonstrate the superior performance of our approach over five commonly-used benchmarks. © 2021. The copyright of this document resides with its authors.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

FairSSD: Understanding Bias in Synthetic Speech Detectors

FairSSD: Understanding Bias in Synthetic Speech Detectors

引用

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Amit Kumar Singh Yadav Kratika Bhagtani Davide Salvi Paolo Bestagini Edward J. Delp Video and Image Processing Lab (VIPER) Purdue University West Lafayette Indiana USA Dipartimento di Elettronica Informazione e Bioingegneria Milano Italy

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Methods that can generate synthetic speech which is perceptually indistinguishable from speech recorded by a human speaker, are easily available. Several incidents report misuse of synthetic speech generated from these methods to commit fraud. To counter such misuse, many methods have been proposed to detect synthetic speech. Some of these detectors are more interpretable, can generalize to detect synthetic speech in the wild and are robust to noise. However, limited work has been done on understanding bias in these detectors. In this work, we examine bias in existing synthetic speech detectors to determine if they will unfairly target a particular gender, age and accent group. We also inspect whether these detectors will have a higher misclassification rate for bona fide speech from speech-impaired speakers w.r.t fluent speakers. Extensive experiments on 6 existing synthetic speech detectors using more than 0.9 million speech signals demonstrate that most detectors are gender, age and accent biased, and future work is needed to ensure fairness. To support future research, we release our evaluation dataset, models used in our study and source code at https://***/viper-purdue/fairssd.

关键词： Computer vision Source coding Conferences Noise Detectors Pattern recognition Fraud

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Method with Edge Awareness for Abnormally Shaped Nuclei Segmentation

An Ensemble Method with Edge Awareness for Abnormally Shaped...

引用

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Yue Han Yang Lei Viktor Shkolnikov Daisy Xin Alicia Auduong Steven Barcelo Jan Allebach Edward J. Delp Video and Image Processing Lab (VIPER) Purdue University West Lafayette Indiana USA HP Inc Palo Alto California USA

Abnormalities in biological cell nuclei shapes are correlated with cell cycle stages, disease states, and various external stimuli. There have been many deep learning approaches that are being used for nuclei segmentation and analysis. In recent years, transformers have performed better than CNN methods on many computer vision tasks. One problem with many deep learning nuclei segmentation methods is acquiring large amounts of annotated nuclei data, which is generally expensive to obtain. In this paper, we propose a Transformer and CNN hybrid ensemble processing method with edge awareness for accurately segmenting abnormally shaped nuclei. We call this method Hybrid Edge Mask R-CNN (HER-CNN), which uses Mask R-CNNs with the ResNet and the Swin-Transformer to segment abnormally shaped nuclei. We add an edge awareness loss to the mask prediction step of the Mask R-CNN to better distinguish the edge difference between the abnormally shaped nuclei and typical oval nuclei. We describe an ensemble processing strategy to combine or fuse individual segmentations from the CNN and the Transformer. We introduce the use of synthetic ground truth image generation to supplement the annotated training images due to the limited amount of data. Our proposed method is compared with other segmentation methods for segmenting abnormally shaped nuclei. We also include ablation studies to show the effectiveness of the edge awareness loss and the use of synthetic ground truth images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Speech Synthesizer Attribution in an Open Set Scenario

Transformer-Based Speech Synthesizer Attribution in an Open ...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Emily R. Bartusiak Edward J. Delp Video and Image Processing Lab School of Electrical and Computer Engineering Purdue University West Lafayette IN

Speech synthesis methods can create realistic-sounding speech, which may be used for fraud, spoofing, and mis-information campaigns. Forensic methods that detect synthesized speech are important for protection against such attacks. Forensic attribution methods provide even more information about the nature of synthesized speech signals because they identify the specific speech synthesis method (i.e., speech synthesizer) used to create a speech signal. Due to the increasing number of realistic-sounding speech synthesizers, we propose a speech attribution method that generalizes to new synthesizers not seen during training. To do so, we investigate speech synthesizer attribution in both a closed set scenario and an open set scenario. In other words, we consider some speech synthesizers to be "known" synthesizers (i.e., part of the closed set) and others to be "unknown" synthesizers (i.e., part of the open set). We represent speech signals as spectrograms and train our proposed method, known as compact attribution transformer (CAT), on the closed set for multi-class classification. Then, we extend our analysis to the open set to attribute synthesized speech signals to both known and unknown synthesizers. We utilize a t-distributed stochastic neighbor embedding (tSNE) on the latent space of the trained CAT to differentiate between each unknown synthesizer. Additionally, we explore poly-1 loss formulations to improve attribution results. Our proposed approach successfully attributes synthesized speech signals to their respective speech synthesizers in both closed and open set scenarios.

关键词： Training Synthesizers Forensics Machine learning Transformers Fraud Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Stochastic Recursive Gradient Descent Optimization-based on Foreground Features of Fisher Vector 14

Stochastic Recursive Gradient Descent Optimization-based on ...

引用

14th International Conference on Digital image processing, ICDIP 2022

作者： Kamaleldin, Mohamed Gamal M. Abu-Bakar, Syed A.R. Sheikh, Usman Ullah Electronics and Communications Engineering Department Arab Academy for Science and Technology Cairo11736 Egypt Computer Vision Video and Image Processing Research Lab School of Electrical Engineering Universiti Teknologi Malaysia Johor Skudai81300 Malaysia

ISBN: (纸本)9781510657564

Human action recognition has been one of the hot topics in computer vision both from the handcrafted and deep learning approaches. In the handcrafted approach, the extracted features are encoded for reducing the size of these features. Amonsgt the state-of-the-art approaches is to encode these visual features using the Gaussian mixture model. However, the size of the codebook is an issue in terms of the computation complexity, especially for large-scale data as it requires encoding using a large codebook. In this paper, we introduced the use of different optimizers to reduce the codebook size while boosting its accuracy. To illustrate the performance, first we use the improved dense trajectories (IDT) to extract the handcrafted features. This is followed with encoding the descriptor using Fisher kernel-based codebook using the Gaussian mixture model. Next, the support vector machine is used to classify the categories. We then use and compare five different Stochastic gradient descent optimization techniques to modify the number of Gaussian components. In this manner we are able to select the discriminative foreground features (as represented by the final number of Gaussian components), and omit the background features. Finally, to show the performance improvement of the proposed method, we implement this technique to two datasets UCF101 and HMDB51. © 2022 SPIE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Speech Synthesizer Attribution in an Open Set Scenario

arXiv

引用

arXiv 2022年

作者： Bartusiak, Emily R. Delp, Edward J. Video and Image Processing Lab School of Electrical and Computer Engineering Purdue University West LafayetteIN United States

Speech synthesis methods can create realisticsounding speech, which may be used for fraud, spoofing, and misinformation campaigns. Forensic methods that detect synthesized speech are important for protection against such attacks. Forensic attribution methods provide even more information about the nature of synthesized speech signals because they identify the specific speech synthesis method (i.e., speech synthesizer) used to create a speech signal. Due to the increasing number of realistic-sounding speech synthesizers, we propose a speech attribution method that generalizes to new synthesizers not seen during training. To do so, we investigate speech synthesizer attribution in both a closed set scenario and an open set scenario. In other words, we consider some speech synthesizers to be "known" synthesizers (i.e., part of the closed set) and others to be "unknown" synthesizers (i.e., part of the open set). We represent speech signals as spectrograms and train our proposed method, known as compact attribution transformer (CAT), on the closed set for multi-class classification. Then, we extend our analysis to the open set to attribute synthesized speech signals to both known and unknown synthesizers. We utilize a t-distributed stochastic neighbor embedding (tSNE) on the latent space of the trained CAT to differentiate between each unknown synthesizer. Additionally, we explore poly-1 loss formulations to improve attribution results. Our proposed approach successfully attributes synthesized speech signals to their respective speech synthesizers in both closed and open set scenarios. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Improving Fairness in Synthetic Speech Detectors

Improving Fairness in Synthetic Speech Detectors

引用

Asilomar Conference on Signals, Systems & Computers

作者： Amit Kumar Singh Yadav Kratika Bhagtani Paolo Bestagini Edward J. Delp Video and Image Processing Lab (VIPER) School of Electrical and Computer Engineering Purdue University West Lafayette Indiana USA Dipartimento di Elettronica Informazione e Bioingegneria Politecnico di Milano Milano Italy

ISBN: (数字)9798350354058

ISBN: (纸本)9798350354065

Many methods have been proposed which can effectively detect synthetic speech. However, a recent study demonstrates that they exhibit bias and a higher false positive rate for bona fide speech from speakers with stuttering speech-impairment as compared to fluent speakers. This limits deploy-ment of these detectors, as this bias can have significant societal and political consequences and can erode the reputation of social platforms using such detectors. This bias may have arisen from the bias in training data used for these detectors. Creating synthetic and bona fide speech with stuttering, and adding it to the training set for mitigating bias, can be time-consuming. In this work, we propose StutterAug, a set of augmentations that simulate three major types of stuttering in speech, namely repetition, prolongation and blocks. We test StutterAug on 3 synthetic speech detectors and examine bias on stuttering speech using more than 28K bona fide stuttering speech. Our results show that detectors trained with StutterAug have on average 13% less bias relative to detector trained without StutterAug. StutterAug also leads to an average relative improvement of 27.96% in detection performance on ASVspoof2019 dataset and 11.27% in generalization performance on In-the-Wild dataset compared to baseline detectors trained without StutterAug.

关键词： Training Computers Deepfakes Forensics Training data Detectors Speech synthesis

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：