检索结果-内蒙古大学图书馆

Speaker Diarization for Low-Resource Languages Through Wav2vec Fine-Tuning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Abdullah, Abdulhady Abas Taher Karim, Sarkhel H. Ahmed, Sara Azad Tariq, Kanar R. Rashid, Tarik A. Artificial Intelligence and Innovation Centre University of Kurdistan Hewler Erbil Iraq Computer Science Department College of Science University of Halabja Kurdistan Region Iraq Computer Engineering Dep Komar University of Science and Technology Iraq Information Technology Department Technical College of Informatics Sulaimani Polytechnic University Sulaymaniyah Iraq

Speaker diarization, a core problem in speech processing, entails partitioning a given audio stream according to the speakers. Even though progress has been made in the development of the models for high-resource languages, there is still a set of specific difficulties in going through a similar process for low-resource languages such as Kurdish: there are very few annotated datasets available;the language has dialects;speakers use code-switching a lot. These challenges are met in this study by training the Wav2Vec 2.0 SSL model on a Kurdish dataset prepared for this purpose. Thanks to transfer learning, it was possible to transfer multilingual representations learnt in other languages to the phonetic and acoustic features of Kurdish speech. The general Diarization Error Rate (DER) was reduced by 7.2%, and the cluster purity increased by 13% when compared to the baseline algorithm. They show that making improvements in any state-of-the-art model can help in enhancing the performance of under-resourced languages. Implications of this work include transcription services for Kurdish-language media programs, as well as speaker segmentation in multilingual call centers, teleconferencing, and videoconferencing systems. Therefore, this work demonstrates that self-supervised and transfer techniques can improve speaker diarization for Kurdish and other low-resource languages with diverse features. The approach provides a base for building effective diarization systems in other understudied languages, which remains essential for speech technology’s equity. © 2025, CC BY.

关键词： Speech enhancement

Enhancing Industrial 4.0 Connectivity: A D2D-Based Algorithm for Blind Spot Mitigation in 5G Future Networks Enabled Smart Industry

学校读者我要写书评

暂无评论

Enhancing Industrial 4.0 Connectivity: A D2D-Based Algorithm...

IEEE Globecom Workshops

作者： Muhammad Farhan Khan Adeel Iqbal Atif Shakeel Adnan Rashid Dirk Pesch Confirm Centre for Smart Manufacturing University College Cork Cork Ireland Department of Electrical and Computer Engineering COMSATS University Islamabad Islamabad Pakistan Dep. of Electrical & Information Engineering Politecnico di Bari Bari Italy

The Industry 4.0 is characterized by the integration of advanced and emerging technologies such as Fifth Generation (5G) and Next-Generation Networks & beyond, Artificial Intelligence (AI), Internet-of- Things (IoT), Machine Learning (ML), Robotics, Automation, Blockchain, Cloud Computing, Edge Computing, Augmented Reality (AR), Virtual Reality (VR) and many others. Despite the widespread adoption of 5G, Wireless Fidelity (Wi-Fi) routers, and other wireless technologies in the industry, there are still areas with limited or no coverage, commonly known as blind spots or coverage holes. The Device-to-Device (D2D) communication enables direct communication without a central entity, known as a coordinator or base station. By leveraging D2D communication, IoT nodes can serve as relays to deal with blind spots. In this research, we propose a novel D2D communication-based algorithm to cope with the challenge of blind spots in IoT -based smart industries. The algorithm focuses on nodes situated in blind spots by establishing connections to the network through nearby IoT nodes that function as relays. We demonstrate through simulations that our approach can effectively remove blind spots, improve coverage, increase throughput, and enhance overall system efficiency.

关键词：

Fed-Haul: A Federated Learning Dual Band Point Multi-Point Backhaul Requirements in 5G Evolution and Beyond 23

学校读者我要写书评

暂无评论

Fed-Haul: A Federated Learning Dual Band Point Multi-Point B...

6th International Conference on Networking, Intelligent Systems and Security, NISS 2023

作者： Chehri, Abdellah Chaibi, Hasna Mettiti, Abderrahmane Saadane, Rachid Jeon, Gwanggil Dep. of Math. and Computer Science Royal Military College of Canada Kingston Canada Supmti Genius Laboratory Hassan Rabat Morocco It Rabat Center Faculty of Sciences Mohammed v University Rabat Morocco SIRC-LAGES-EHTP Hassania School of Public Works Casalanca Morocco Department of Embedded Systems Engineering Incheon National University Korea Republic of

ISBN: (纸本)9798400700194

The rapid adoption of smartphones and the explosive growth of data traffic due to these devices have been phenomenal. As the world anticipates more connected devices - the Internet of Things (IoT), vehicle-to-vehicle (V2V) communications, and wearable devices - and more value-added applications and services (ultra-high-definition video, 360° video, virtual reality, smart cars, etc.), leading industry experts are calling for the sixth generation (6G) networks. Federated learning is a common distributed machine learning framework. Through the training of the global model, the problems of large communication overhead and data privacy protection in traditional centralized machine learning are solved. Federated learning (FL) is essential in optimizing wireless communication networks' resources. On the other hand, wireless communications are crucial for FL. Therefore, the purpose of this survey paper is to bridge this gap in the literature by discussing the interdep.ndency between FL and backhaul wireless communications. © 2023 ACM.

关键词： 5G mobile communication systems

COMPONENT TWIN-WIDTH AS A PARAMETER FOR BINARY-CSP AND ITS SEMIRING GENERALISATIONS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Baril, Ambroise Couceiro, Miguel Lagerkvist, Victor Université de Lorraine CNRS LORIA NancyF-54000 France Dep. Computer and Information Science Linköpings Universitet Sweden

We investigate the fine-grained and the parameterized complexity of several generalizations of binary constraint satisfaction problems (BINARY-CSPs), that subsume variants of graph colouring problems. Our starting point is the observation that several algorithmic approaches that resulted in complexity upper bounds for these problems, share a common structure. We thus explore an algebraic approach relying on semirings that unifies different generalizations of BINARY-CSPs (such as the counting, the list, and the weighted versions), and that facilitates a general algorithmic approach to efficiently solving them. The latter is inspired by the (component) twin-width parameter introduced by Bonnet et al., which we generalize via edge-labelled graphs in order to formulate it to arbitrary binary constraints. We consider input instances with bounded component twin-width, as well as constraint templates of bounded component twin-width, and obtain an FPT algorithm as well as an improved, exponential-time algorithm, for broad classes of binary constraints. We illustrate the advantages of this framework by instantiating our general algorithmic approach on several classes of problems (e.g., the H-coloring problem and its variants), and showing that it improves the best complexity upper bounds in the literature for several well-known problems. © 2022, CC BY.

关键词： Constraint satisfaction problems

Speech Emotion Recognition Using Deep Learning Techniques and Augmented Features

学校读者我要写书评

暂无评论

Speech Emotion Recognition Using Deep Learning Techniques an...

International Conference on Electrical engineering, computer science and Informatics (EECSI)

作者： Shahed Mohammadi Niloufar Hemati Ali Hashemi Haniye Zandiye Computer Science & Systems Engineering Dep. Ayandegan University Mazandaran Iran Islamic Azad University Central Tehran Branch Tehran Iran Qom University of Technology Qom Iran

This paper presents a study on speech emotion recognition using deep learning techniques. The focus is on utilizing the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) and the Toronto Emotional Speech Set (TESS) datasets. The proposed approach involves preprocessing the audio signals by converting them into a sequence of numbers and normalizing them using max normalization. Furthermore, the signals are augmented using three methods: noise with a 0.015 noise rate, pitch adjustment, and a combination of noise with a 0.03 noise rate and pitch adjustment. The extraction of audio features includes a combination of two features, namely Mel Frequency Cepstrum Coefficients (MFCC) and Root Mean Square (RMS) energy, which provide distinct information from each other. These features are then used to train a CNN for emotion classification. Experimental results demonstrate the effectiveness of the proposed approach in accurately recognizing emotions from speech signals. The proposed approach achieves an accuracy of 93.6% on the RAVDESS dataset and 99.9% on the TESS dataset. These results highlight the potential of the proposed approach in practical applications such as speech therapy and human-computer interaction.

关键词：

Enhanced SNR Based Admission Control Algorithm for Vehicular Ad-Hoc Network 23

学校读者我要写书评

暂无评论

Enhanced SNR Based Admission Control Algorithm for Vehicular...

Proceedings of the 7th International Conference on Future Networks and Distributed Systems

作者： Aws Zuhair Sameen Mohammed Hasan Alwan Mayssam Saad Kadhum Yousif I Hammadi Mokhalad Abdulameer Kadhim Alsaeedi Ahmed Aziz Mohammed Saleh Ali Muthanna Department of Medical Instrumentation Engineering Techniques Al-Farahidi University Iraq Department of Communications Engineering University of Diyala Iraq Dep. of Medical Instruments Engineering Techniques Bilad Alrafidain University College Iraq Department of computer science Benha university Egypt and International Business Management Department Tashkent State University of Economics Uzbekistan Institute of Computer Technologies and Information Security Southern Federal University Russia

ISBN: (纸本)9798400709036

Vehicular Ad-hoc Network (VANET) becomes a fundamental subcategory of mobile ad-hoc networks that provides vehicles to communicate with each other and with roadside infrastructure smartly. Various VANET performance challenges are considered in terms of Quality of Service (QoS) due to vehicle speed and transmission rates. Different problems cause performance degradation as performance anomaly where high rates of vehicles have to meet the speed of the low rates vehicle while transmitting data. In this paper, a QoS-aware Signal to Noise Ratio (SNR) admission control mechanism (QASAC) is proposed to handle the performance anomaly problem while maintaining the QoS levels for different traffic types. QASAC has been compared against the latest SNR based admission control mechanism. QASAC has enhanced the performance of data delivery up to 23% in terms of data dropping rates for high priority traffic.

关键词：

Solutions for Digital Interaction of a Resilient Energy Community in a Service-oriented Framework 12

学校读者我要写书评

暂无评论

Solutions for Digital Interaction of a Resilient Energy Comm...

12th International Conference and Exposition on Electrical and Power engineering, EPE 2022

作者： Sanduleac, Mihai Ionescu, Constantin Mandis, Alexandru Gropa, Victor Efremov, Cristina Sanduleac, Vlad Department of Power Systems Faculty of Energy Engineering University Politehnica of Bucharest Bucharest Romania Dep. of Energy Generation and Use Faculty of Energy Engineering University Politehnica of Bucharest Bucharest Romania Faculty of Energetics and Electrical Engineering Technical University of Moldova Chisinau Moldova Department of Computer Science and Engineering Faculty of Automatic Control and Computers University Politehnica of Bucharest Romania

ISBN: (数字)9781665489942

ISBN: (纸本)9781665489942

Energy communities are emerging entities which need their own information and Communication System. Resilience is a key metric of such communities, and it has to be implemented for both energy supply versus public network outages and for its information system versus cyber-attacks, acting as cyber-citadels which have to resist external malicious attacks while having also digital interactions with external entities. The paper presents solutions for a resilient energy community with appropriate implementations of digital interaction for data exchange, in order to acquire external energy service for specialized companies and to deliver also information and communication-related services for external users. Principles of a Contractual Data Protection Regulation are presented, as an adaptation of data protection tailored for automated energy services and based on secure data exchange. The principles are verified in a demonstration project which has also external entities with digital interaction. © 20XX IEEE.

关键词： Cybersecurity

Speech Emotion Recognition using Supervised Deep Recurrent System for Mental Health Monitoring

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Elsayed, Nelly ElSayed, Zag Asadizanjani, Navid Ozer, Murat Abdelgawad, Ahmed Bayoumi, Magdy School of Information Technology University of Cincinnati OH United States Dep. of Electrical & Computer Engineering University of Florida FL United States School of Engineering and Technology Central Michigan University MI United States Dep. of Electrical & Computer Engineering University of Louisiana at Lafayette LA United States

Understanding human behavior and monitoring mental health are essential to maintaining the community and society's safety. As there has been an increase in mental health problems during the COVID-19 pandemic due to uncontrolled mental health, early detection of mental issues is crucial. Nowadays, the usage of Intelligent Virtual Personal Assistants (IVA) has increased worldwide. Individuals use their voices to control these devices to fulfill requests and acquire different services. This paper proposes a novel deep learning model based on the gated recurrent neural network and convolution neural network to understand human emotion from speech to improve their IVA services and monitor their mental health. Copyright © 2022, The Authors. All rights reserved.

关键词： Recurrent neural networks

Reducing Overconfidence Predictions for Autonomous Driving Perception

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Melotti, Gledson Premebida, Cristiano Bird, Jordan J. Faria, Diego R. Gonçalves, Nuno Federal Institute of Espirito Santo Brazil The Dep. of Electrical and Computer Engineering University of Coimbra-Portugal Portugal Department of Computer Science Nottingham Trent University United Kingdom School of Physics Engineering and Computer Science University of Hertfordshire United Kingdom Dep. of Electrical and Computer Engineering University of Coimbra-Portugal Portuguese Mint and Official Printing Office Lisbon Portugal

In state-of-the-art deep learning for object recognition, Softmax and Sigmoid layers are most commonly employed as the predictor outputs. Such layers often produce overconfidence predictions rather than proper probabilistic scores, which can thus harm the decision-making of 'critical' perception systems applied in autonomous driving and robotics. Given this, we propose a probabilistic approach based on distributions calculated out of the Logit layer scores of pre-trained networks which are then used to constitute new decision layers based on Maximum Likelihood (ML) and Maximum a-Posteriori (MAP) inference. We demonstrate that the hereafter called ML and MAP layers are more suitable for probabilistic interpretations than Softmax and Sigmoid-based predictions for object recognition. We explore distinct sensor modalities via RGB images and LiDARs (RV: range-view) data from the KITTI and Lyft Level-5 datasets, where our approach shows promising performance compared to the usual Softmax and Sigmoid layers, with the benefit of enabling interpretable probabilistic predictions. Another advantage of the approach introduced in this paper is that the so-called ML and MAP layers can be implemented in existing trained networks, that is, the approach benefits from the output of the Logit layer of pre-trained networks. Thus, there is no need to carry out a new training phase since the ML and MAP layers are used in the test/prediction phase. The Classification results are presented using reliability diagrams, while detection results are illustrated using precision-recall *** Codes 68T10 Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting