A significant portion of the global population speaks multiple languages, including many low-resource languages on which current multilingual ASR models perform poorly. To improve ASR performance on these languages, m...
详细信息
A significant portion of the global population speaks multiple languages, including many low-resource languages on which current multilingual ASR models perform poorly. To improve ASR performance on these languages, models are typically fine-tuned on low-resource data with only a small subset of parameters adjusted to prevent overfitting. Traditionally, separate models are fine-tuned for each target language. During inference, a specific model is selected based on the language to be transcribed. However, in applications such as smart home devices, where multilingual users may vary their language use unpredictably, it becomes challenging to pre-select the appropriate model when the language is unknown in advance. To address this, this paper introduces a two-stage regularization-based continual learning method that adapts a single model to transcribe both source and target languages while minimizing overfitting. In the first stage, strong regularization is applied to update all parameters, and in the second, regularization is relaxed to enhance learning capacity. By adapting Whisper, a state-of-the-art speech foundation model that supports MASR, to 10 h of data for each of 2 target languages from Common Voice, the results show that our method can reduce average word error rate in the source and target languages from 18.59% to 15.52%.
As an important enabler for changing people’s lives, advances in artificial intelligence (AI)-based applications and services are on the rise, despite being hindered by efficiency and latency issues. By focusing on dee...
详细信息
ISBN:
(数字)9789811561863
ISBN:
(纸本)9789811561856;9789811561887
As an important enabler for changing people’s lives, advances in artificial intelligence (AI)-based applications and services are on the rise, despite being hindered by efficiency and latency issues. By focusing on deep learning as the most representative technique of AI, this book provides a comprehensive overview of how AI services are being applied to the network edge near the data sources, and demonstrates how AI and edge computing can be mutually beneficial. To do so, it introduces and discusses: 1) edge intelligence and intelligent edge; and 2) their implementation methods and enabling technologies, namely AI training and inference in the customized edge computing framework. Gathering essential information previously scattered across the communication, networking, and AI areas, the book can help readers to understand the connections between key enabling technologies, e.g. a) AI applications in edge; b) AI inference in edge; c) AI training for edge; d) edge computing for AI; and e)using AI to optimize edge. After identifying these five aspects, which are essential for the fusion of edge computing and AI, it discusses current challenges and outlines future trends in achieving more pervasive and fine-grained intelligence with the aid of edge computing.
This handbook presents the key topics in the area of computer architecture covering from the basic to the most advanced topics, including software and hardware design methodologies. It will provide readers with t...
详细信息
ISBN:
(数字)9789819793143
ISBN:
(纸本)9789819793136
This handbook presents the key topics in the area of computer architecture covering from the basic to the most advanced topics, including software and hardware design methodologies. It will provide readers with the most comprehensive updated reference information covering applications in single core processors, multicore processors, application-specific processors, reconfigurable architectures, emerging computing architectures, processor design and programming flows, test and verification. This information benefits the readers as a full and quick technical reference with a high-level review of computer architecture technology, detailed technical descriptions and the latest practical applications.
Distributed Collaborative Machine Learning (DCML) has emerged in artificial intelligence-empowered edge computing environments, such as the Industrial Internet of Things (IIoT), to process tremendous data generated by...
详细信息
Distributed Collaborative Machine Learning (DCML) has emerged in artificial intelligence-empowered edge computing environments, such as the Industrial Internet of Things (IIoT), to process tremendous data generated by smart devices. However, parallel DCML frameworks require resource-constrained devices to update the entire Deep Neural Network (DNN) models and are vulnerable to reconstruction attacks. Concurrently, the serial DCML frameworks suffer from training efficiency problems due to their serial training nature. In this paper, we propose a Model Pruning-enabled Federated Split Learning framework (MP-FSL) to reduce resource consumption with a secure and efficient training scheme. Specifically, MP-FSL compresses DNN models by adaptive channel pruning and splits each compressed model into two parts that are assigned to the client and the server. Meanwhile, MP-FSL adopts a novel aggregation algorithm to aggregate the pruned heterogeneous models. We implement MP-FSL with a real FL platform to evaluate its performance. The experimental results show that MP-FSL outperforms the state-of-the-art frameworks in model accuracy by up to 1.35%, while concurrently reducing storage and computational resource consumption by up to 32.2% and 26.73%, respectively. These results demonstrate that MP-FSL is a comprehensive solution to the challenges faced by DCML, with superior performance in both reduced resource consumption and enhanced model performance.
The advancement of the Internet of Medical Things (IoMT) has led to the emergence of various health and emotion care services, e.g., health monitoring. To cater to increasing computational requirements of IoMT service...
详细信息
The advancement of the Internet of Medical Things (IoMT) has led to the emergence of various health and emotion care services, e.g., health monitoring. To cater to increasing computational requirements of IoMT services, Mobile Edge computing (MEC) has emerged as an indispensable technology in smart health. Benefiting from the cost-effectiveness of deployment, unmanned aerial vehicles (UAVs) equipped with MEC servers in Non-Orthogonal Multiple Access (NOMA) have emerged as a promising solution for providing smart health services in proximity to medical devices (MDs). However, the escalating number of MDs and the limited availability of communication resources of UAVs give rise to a significant increase in transmission latency. Moreover, due to the limited communication range of UAVs, the geographically-distributed MDs lead to workload imbalance of UAVs, which deteriorates the service response delay. To this end, this paper proposes a UAV-enabled Distributed computation Offloading and Power control method with Multi-Agent, named DOPMA, for NOMA-based IoMT environment. Specifically, this paper introduces computation and transmission queue models to analyze the dynamic characteristics of task execution latency and energy consumption. Moreover, a credit assignment scheme-based reward function is designed considering both system-level rewards and rewards tailored to each MD, and an improved multi-agent deep deterministic policy gradient algorithm is developed to derive offloading and power control decisions independently. Extensive simulations demonstrate that the proposed method outperforms existing schemes, achieving \(7.1\%\) reduction in energy consumption and \(16\%\) decrease in average delay.
The Anchor-based Multi-view Subspace Clustering (AMSC) has turned into a favourable tool for large-scale multi-view clustering. However, there still exist some limitations to the current AMSC approaches. First, they t...
详细信息
The Anchor-based Multi-view Subspace Clustering (AMSC) has turned into a favourable tool for large-scale multi-view clustering. However, there still exist some limitations to the current AMSC approaches. First, they typically recover anchor graph structure in the original linear space, restricting their feasibility for nonlinear scenarios. Second, they usually overlook the potential benefits of jointly capturing the inter-view and intra-view information for enhancing the anchor representation learning. Third, these approaches mostly perform anchor-based subspace learning by a specific matrix norm, neglecting the latent high-order correlation across different views. To overcome these limitations, this paper presents an efficient and effective approach termed Large-scale Tensorized Multi-view Kernel Subspace Clustering (LTKMSC). Different from the existing AMSC approaches, our LTKMSC approach exploits both inter-view and intra-view awareness for anchor-based representation building. Concretely, the low-rank tensor learning is leveraged to capture the high-order correlation (i.e., the inter-view complementary information) among distinct views, upon which the \(l_{1,2}\) norm is imposed to explore the intra-view anchor graph structure in each view. Moreover, the kernel learning technique is leveraged to explore the nonlinear anchor-sample relationships embedded in multiple views. With the unified objective function formulated, an efficient optimization algorithm that enjoys low computational complexity is further designed. Extensive experiments on a variety of multi-view datasets have confirmed the efficiency and effectiveness of our approach when compared with the other competitive approaches.
暂无评论