检索结果-内蒙古大学图书馆

Accounting for the Special Role of Infrastructure-assisted Collective Perception

学校读者我要写书评

暂无评论

Accounting for the Special Role of Infrastructure-assisted C...

International Conference on Intelligent Transportation

作者： Florian Alexander Schiegg Anna–Lisa Rueeck Jörg Gamerdinger Hugues Tchouankem Edmir Xhoxhi Georg Volk Distributed Intelligence and Systems Corporate Research Robert Bosch GmbH Hildesheim Germany Function Development 3D Surround View Engineering Parking Functions Robert Bosch GmbH Feuerbach Germany Department of Computer Science Embedded Systems Group University of Tübingen Tübingen Germany Institute of Communication Technology Leibniz University Hanover Hanover Germany

The number of traffic participants has increased exponentially over the past century, making a traffic accident the most likely cause of death for children and young adults today. Vehicle-to-Everything (V2X) communication is regarded as one of the most promising emerging technologies to enhance road safety. It allows traffic participants to exchange relevant information to increase their environmental perception. Cooperative Awareness, a V2X service that is already being deployed in Europe, enables road users to share their dynamic states. Collective Perception (CP), currently in the final stage of standardization in the different regions of the world, enables the exchange of sensor-detected objects. The latter is thus not only relevant for connected vehicles but can further be used by sensor-equipped infrastructure to support vehicular perception, opening a whole new range of possibilities. The objective of this work is to investigate mechanisms to account for the special role of Infrastructure-assisted Collective Perception (ICP). Packet duplication is introduced for ICP to enhance the communication reliability. Additionally, different message generation rules prioritizing ICP are proposed and compared based on the enabled environmental perception. Simulations show significant improvements of the average precision, reaching an average increase of about 60% for ICP in comparison to V2V -based CP in scenarios with low connected vehicle densities.

关键词：

Self Supervised Adversarial Domain Adaptation for Cross-Corpus and Cross-Language Speech Emotion Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Latif, Siddique Rana, Rajib Khalifa, Sara Jurdak, Raja Schuller, Björn Springfield4301 Australia Distributed Sensing Systems Group Data61 CSIRO PullenvaleQLD4069 Australia Springfield4301 Australia Brisbane4000 Australia GLAM - the Group on Language Audio and Music Imperial College London United Kingdom Embedded Intelligence for Health Care and Wellbeing University of Augsburg Germany

Despite the recent advancement in speech emotion recognition (SER) within a single corpus setting, the performance of these SER systems degrades significantly for cross-corpus and cross-language scenarios. The key reason is the lack of generalisation in SER systems towards unseen conditions, which causes them to perform poorly in cross-corpus and cross-language settings. Recent studies focus on utilising adversarial methods to learn domain generalised representation for improving cross-corpus and cross-language SER to address this issue. However, many of these methods only focus on cross-corpus SER without addressing the cross-language SER performance degradation due to a larger domain gap between source and target language data. This contribution proposes an adversarial dual discriminator (ADDi) network that uses the three-players adversarial game to learn generalised representations without requiring any target data labels. We also introduce a self-supervised ADDi (sADDi) network that utilises self-supervised pre-training with unlabelled data. We propose synthetic data generation as a pretext task in sADDi, enabling the network to produce emotionally discriminative and domain invariant representations and providing complementary synthetic data to augment the system. The proposed model is rigorously evaluated using five publicly available datasets in three languages and compared with multiple studies on cross-corpus and cross-language SER. Experimental results demonstrate that the proposed model achieves improved performance compared to the state-of-the-art methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

A Novel Policy for Pre-trained Deep Reinforcement Learning for Speech Emotion Recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Rajapakshe, Thejan Rana, Rajib Khalifa, Sara Schuller, Björn W. Liu, Jiajun University of Southern Queensland Australia Distributed Sensing Systems Group Data61 CSIRO Australia GLAM - Group on Language Audio & Music Imperial College London United Kingdom Embedded Intelligence for Health Care & Wellbeing University of Augsburg Germany

Reinforcement Learning (RL) is a semi-supervised learning paradigm where an agent learns by interacting with an environment. Deep learning in combination with RL provides an efficient method to learn how to interact with the environment called Deep Reinforcement Learning (deep RL). Deep RL has gained tremendous success in gaming - such as AlphaGo, but its potential has rarely being explored for challenging tasks like Speech Emotion Recognition (SER). Deep RL being used for SER can potentially improve the performance of an automated call centre agent by dynamically learning emotion-aware responses to customer queries. While the policy employed by the RL agent plays a major role in action selection, there is no current RL policy tailored for SER. In addition, an extended learning period is a general challenge for deep RL, which can impact the speed of learning for SER. Therefore, in this paper, we introduce a novel policy - the "Zeta policy" which is tailored for SER and apply pre-training in deep RL to achieve a faster learning rate. Pre-training with a cross dataset was also studied to discover the feasibility of pre-training the RL agent with a similar dataset in a scenario where real environmental data is not available. The IEMOCAP and SAVEE datasets were used for the evaluation with the problem being to recognise the four emotions happy, sad, angry, and neutral in the utterances provided. The experimental results show that the proposed "Zeta policy" performs better than existing policies. They also support that pre-training can reduce the training time and is robust to a cross-corpus scenario. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

Survey of deep representation learning for speech emotion recognition

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2021年

作者： Latif, Siddique Rana, Rajib Khalifa, Sara Jurdak, Raja Qadir, Junaid Schuller, Björn Australia and Distributed Sensing Systems Group Data61—CSIRO Australia Australia Distributed Sensing Systems Group Data61—CSIRO University of New South Wales University of Queensland Australia Australia Qatar University Doha Qatar Lahore Pakistan GLAM – the Group on Language Audio and Music Imperial College London United Kingdom Embedded Intelligence for Health Care and Wellbeing University of Augsburg Germany

Traditionally, speech emotion recognition (SER) research has relied on manually handcrafted acoustic features using feature engineering. However, the design of handcrafted features for complex SER tasks requires significant manual effort, which impedes generalisability and slows the pace of innovation. This has motivated the adoption of representation learning techniques that can automatically learn an intermediate representation of the input signal without any manual feature engineering. Representation learning has led to improved SER performance and enabled rapid innovation. Its effectiveness has further increased with advances in deep learning (DL), which has facilitated deep representation learning where hierarchical representations are automatically learned in a data-driven manner. This paper presents the first comprehensive survey on the important topic of deep representation learning for SER. We highlight various techniques, related challenges and identify important future areas of research. Our survey bridges the gap in the literature since existing surveys either focus on SER with hand-engineered features or representation learning in the general setting without focusing on SER. © 2021, CC BY.

关键词： Surveys

Deep reinforcement learning with pre-training for time-efficient training of automatic speech recognition

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Rajapakshe, Thejan Latif, Siddique Rana, Rajib Khalifa, Sara Schuller, Björn W. University of Southern Queensland Australia Distributed Sensing Systems Group Data61 CSIRO Australia GLAM - Group on Language Audio & Music Imperial College London United Kingdom ZD.B Chair of Embedded Intelligence for Health Care & Wellbeing University of Augsburg Germany

Deep reinforcement learning (deep RL) is a combination of deep learning with reinforcement learning principles to create efficient methods that can learn by interacting with its environment. This has led to breakthroughs in many complex tasks, such as playing the game "Go", that were previously difficult to solve. However, deep RL requires significant training time making it difficult to use in various real-life applications such as Human-Computer Interaction (HCI). In this paper, we study pre-training in deep RL to reduce the training time and improve the performance of Speech Recognition, a popular application of HCI. To evaluate the performance improvement in training we use the publicly available "Speech Command" dataset, which contains utterances of 30 command keywords spoken by 2,618 speakers. Results show that pre-training with deep RL offers faster convergence compared to non-pre-trained RL while achieving improved speech recognition accuracy. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

Deep Architecture Enhancing Robustness to Noise, Adversarial Attacks, and Cross-corpus Setting for Speech Emotion Recognition

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Latif, Siddique Rana, Rajib Khalifa, Sara Jurdak, Raja Schuller, Björn W. University of Southern Queensland Australia Distributed Sensing Systems Group Data61 CSIRO Australia University of New South Wales Australia Queensland University of Technology Australia GLAM – Group on Language Audio & Music Imperial College London United Kingdom Chair of Embedded Intelligence for Health Care and Wellbeing University of Augsburg Germany

Speech emotion recognition systems (SER) can achieve high accuracy when the training and test data are identically distributed, but this assumption is frequently violated in practice and the performance of SER systems plummet against unforeseen data shifts. The design of robust models for accurate SER is challenging, which limits its use in practical applications. In this paper we propose a deeper neural network architecture wherein we fuse DenseNet, LSTM and Highway Network to learn powerful discriminative features which are robust to noise. We also propose data augmentation with our network architecture to further improve the robustness. We comprehensively evaluate the architecture coupled with data augmentation against (1) noise, (2) adversarial attacks and (3) cross-corpus settings. Our evaluations on the widely used IEMOCAP and MSP-IMPROV datasets show promising results when compared with existing studies and state-of-the-art models. Copyright © 2020, The Authors. All rights reserved.

关键词： Network architecture

Augmenting Generative Adversarial Networks for Speech Emotion Recognition

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Latif, Siddique Asim, Muhammad Rana, Rajib Khalifa, Sara Jurdak, Raja Schuller, Björn W. University of Southern Queensland Australia Distributed Sensing Systems Group Data61 CSIRO Australia Information Technology University Lahore Pakistan University of New South Wales Australia Queensland University of Technology Australia GLAM – Group on Language Audio & Music Imperial College London United Kingdom Chair of Embedded Intelligence for Health Care and Wellbeing University of Augsburg Germany

Generative adversarial networks (GANs) have shown potential in learning emotional attributes and generating new data samples. However, their performance is usually hindered by the unavailability of larger speech emotion recognition (SER) data. In this work, we propose a framework that utilises the mixup data augmentation scheme to augment the GAN in feature learning and generation. To show the effectiveness of the proposed framework, we present results for SER on (i) synthetic feature vectors, (ii) augmentation of the training data with synthetic features, (iii) encoded features in compressed representation. Our results show that the proposed framework can effectively learn compressed emotional representations as well as it can generate synthetic samples that help improve performance in within-corpus and cross-corpus evaluation. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

Pre-training in deep reinforcement learning for automatic speech recognition

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Rajapakshe, Thejan Rana, Rajib Latif, Siddique Khalifa, Sara Schuller, Björn W. University of Southern Queensland Australia Distributed Sensing Systems Group Data61 CSIRO Australia GLAM - Group on Language Audio & Music Imperial College London United Kingdom ZD.B Chair of Embedded Intelligence for Health Care & Wellbeing University of Augsburg Germany

Deep reinforcement learning (deep RL) is a combination of deep learning with reinforcement learning principles to create efficient methods that can learn by interacting with its environment. This led to breakthroughs in many complex tasks that were previously difficult to solve. However, deep RL requires a large amount of training time that makes it difficult to use in various real-life applications like human-computer interaction (HCI). Therefore, in this paper, we study pre-training in deep RL to reduce the training time and improve the performance in speech recognition, a popular application of HCI. We achieve significantly improved performance in less time on a publicly available speech command recognition dataset. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning

Self-Awareness for Autonomous systems

学校读者我要写书评

暂无评论

PROCEEDINGS OF THE IEEE 2020年第7期108卷 971-975页

作者： Dutt, Nikil Regazzoni, Carlo S. Rinner, Bernhard Yao, Xin Nikil Dutt (Fellow IEEE) received the Ph.D. degree from the University of Illinois at Urbana–Champaign Champaign IL USA in 1989.""He is currently a Distinguished Professor of computer science (CS) cognitive sciences and electrical engineering and computer sciences (EECS) with the University of California at Irvine Irvine CA USA. He is a coauthor of seven books. His research interests include embedded systems electronic design automation (EDA) computer architecture distributed systems healthcare Internet of Things (IoT) and brain-inspired architectures and computing.""Dr. Dutt is a Fellow of ACM. He was a recipient of the IFIP Silver Core Award. He has received numerous best paper awards. He serves as the Steering Committee Chair of the IEEE/ACM Embedded Systems Week (ESWEEK). He is also on the steering organizing and program committees of several premier EDA and embedded system design conferences and workshops. He has served on the Editorial Boards for the IEEE Transactions on Very Large Scale Integration (VLSI) Systems and the ACM Transactions on Embedded Computing Systems and also previously served as the Editor-in-Chief (EiC) for the ACM Transactions on Design Automation of Electronic Systems. He served on the Advisory Boards of the IEEE Embedded Systems Letters the ACM Special Interest Group on Embedded Systems the ACM Special Interest Group on Design Automationt and the ACM Transactions on Embedded Computing Systems. Carlo S. Regazzoni (Senior Member IEEE) received the M.S. and Ph.D. degrees in electronic and telecommunications engineering from the University of Genoa Genoa Italy in 1987 and 1992 respectively.""He is currently a Full Professor of cognitive telecommunications systems with the Department of Electrical Electronics and Telecommunication Engineering and Naval Architecture (DITEN) University of Genoa and a Co-Ordinator of the Joint Doctorate on Interactive and Cognitive Environments (JDICE) international Ph.D. course started initially as EU Erasmus Mundus Project and

Autonomous systems are able to make decisions and potentially take actions without direct human intervention, which requires some knowledge about the system and its environment as well as goal-oriented reasoning. In computer systems, one can derive such behavior from the concept of a rational agent with autonomy (“control over its own actions”), reactivity (“react to events from the environment”), proactivity (“act on its own initiative”), and sociality (“interact with other agents”) as fundamental properties \n[1]\n. Autonomous systems will undoubtedly pervade into our everyday lives, and we will find them in a variety of domains and applications including robotics, transportation, health care, communications, and entertainment to name a few. \nThe articles in this month’s special issue cover concepts and fundamentals, architectures and techniques, and applications and case studies in the exciting area of self-awareness in autonomous systems.

关键词： Special issues and sections Autonomous systems Self-aware Robot sensing systems Computational modeling