A low-resource environment has limitations in terms of resources, such as limited network availability and low-powered computing devices. In such environments, it is arguably more difficult to set up new software systems, maintain existing software,...
With the development of continuous speech recognition technology, users have put forward higher requirements in terms of speech recognition accuracy. Low-resource speech recognition, as a typical speech recognition technology under restricted conditi...
The most challenging issue with low-resource languages is the difficulty of obtaining enough language resources. In this paper, we propose a language service framework for low-resource languages that enables the automatic creation and customization o...
Voice activation systems are used to find a pre-defined word or phrase in the audio stream. Industry solutions, such as “OK, Google” for Android devices, are trained with millions of samples. In this work, we propose and investigate several ways to t...
Cervical cancer is one of the most significant global health inequities of our time and is the fourth most common cancer in women worldwide, disproportionally affecting developing countries where the disease burden is 84%. Sometimes referred to as pr...
Despite the many proposals to solve the neural machine translation (NMT) problem of low-resource languages, it continues to be difficult. The issue becomes even more complicated when few resources cover only a single domain. In this paper, we discuss...
The recent trend toward the application of deep structured techniques has revealed the limits of huge models in natural language processing. This has reawakened the interest in traditional machine learning algorithms, which have proved still to be co...
4 February 2021
We provide an overview of the challenges that low-resource setting cities are facing, including a lack of global implementation of cancer screening programs, accurate data and statistics that may aid the health authorities and guide future public hea...
Building an effective automatic speech recognition system typically requires a large amount of high-quality labeled data; However, this can be challenging for low-resource languages. Currently, self-supervised contrastive learning has shown promising...
A fundamental aspect in the evolution of Time-to-Digital Converters (TDCs) implemented within Field-Programmable Gate Arrays (FPGAs), given the increasing demand for detection channels, is the optimization of resource utilization. This study reviews...
One important issue that affects the performance of neural machine translation is the scale of available parallel data. For low-resource languages, the amount of parallel data is not sufficient, which results in poor translation quality. In this pape...
The emergence of large language models (LLMs) has revolutionized the trajectory of NLP research. Transformers, combined with attention mechanisms, have increased computational power, and massive datasets have led to the emergence of pre-trained large...
In low-resource speech recognition, the performance of the Whisper model is often limited by the size of the available training data. To address this challenge, this paper proposes a training optimization method for the Whisper model that integrates...
Advancements in artificial intelligence (AI) for point-of-care ultrasound (POCUS) have ushered in new possibilities for medical diagnostics in low-resource settings. This review explores the current landscape of AI applications in POCUS across these...
Previous works trained the Transformer and its variants end-to-end and achieved remarkable translation performance when there are huge parallel sentences available. However, these models suffer from the data scarcity problem in low-resource machine t...
Named entity recognition (NER) is an important task in the processing of natural language, which needs to determine entity boundaries and classify them into pre-defined categories. For low-resource languages, most state-of-the-art systems require ten...
3 March 2023
Resource-based cities (RBCs) are not only important for ensuring national resource and energy security, but they also face serious ecological and environmental problems. To achieve China’s carbon peaking and neutrality goals in the coming years...
Neural machine translation models are guided by loss function to select source sentence features and generate results close to human annotation. When the data resources are abundant, neural machine translation models can focus on the features used to...
We aim to identify the engagement strategies that higher education students, engaging in emergency online learning in low-resource settings, perceive to be effective. We conducted a sequential mixed-methods study based on Moore’s interaction fr...
Barriers to cancer care, including transportation and Internet insecurity, are of special concern in low-resource communities. A patient-centered, telehealth-based, barrier-focused lay navigator program may mitigate such barriers. We share insights f...
Simulation-based clinical education is a useful strategy for teaching, learning, and assessing clinical competence in health professions education. However, the use of simulation-based clinical nursing education (SBCNE) in low-resource settings such...
Architectural design plays a crucial role in sustainable city development. In fast-growing cities in developing countries, it can be a challenge to reach sustainable results. In this paper, we propose the use of Empathic Design, borrowed from the hum...
To overcome the challenges of low positioning accuracy and inefficient resource utilization in cooperative target localization by unmanned aerial vehicles (UAVs) in complex environments, this paper presents a cooperative localization algorithm that i...
Latin Cuengh is a low-resource dialect that is prevalent in select ethnic minority regions in China. This language presents unique challenges for intelligent research and preservation efforts, primarily due to its oral tradition and the limited avail...
Today, various interactive tools or partially available artificial intelligence applications are actively used in educational processes to solve multiple problems for resource-rich languages, such as English, Spanish, French, etc. Unfortunately, the...
Address parsing is a crucial task in natural language processing, particularly for Chinese addresses. The complex structure and semantic features of Chinese addresses present challenges due to their inherent ambiguity. Additionally, different task sc...
Promoting the sharing of idle resources to community residents is a potential means to building a low-carbon community. This study examined three communities with different attributes (college/university, middle and high income, and the elderly). An...
Automatic Speech Recognition (ASR) systems have made consistent advancements, achieving notable improvements in state-of-the-art performance across various languages. However, their effectiveness often declines significantly in low-resource settings,...
Background: Implementing effective interprofessional communication (IPC) in low-resource settings is challenging, primarily due to limited awareness and understanding of the concept. This analysis examined the concept of effective IPC for patient saf...
Endangered language generally has low-resource characteristics, as an immaterial cultural resource that cannot be renewed. Automatic speech recognition (ASR) is an effective means to protect this language. However, for low-resource language, native s...
This article presents a transfer-learning-based method to improve the synthesized speech quality of the low-resource Dungan language. This improvement is accomplished by fine-tuning a pre-trained Mandarin acoustic model to a Dungan language acoustic...
This paper describes work on the morphological and syntactic annotation of Sumerian cuneiform as a model for low resource languages in general. Cuneiform texts are invaluable sources for the study of history, languages, economy, and cultures of Ancie...
The developed world has focused on Web preservation compared to the developing world, especially news preservation for future generations. However, the news published online is volatile because of constant changes in the technologies used to dissemin...
This study examines the low-carbon economy, agricultural products, and the resource environment as three interconnected subsystems, establishing an evaluation framework for their coordinated growth across eight regions of China. The results highlight...
The rapid spread of misinformation threatens public safety and social stability. Although deep learning-based detection methods have achieved promising results, their effectiveness heavily relies on large amounts of labeled data, limiting their appli...
More than 783 million people worldwide are currently without access to clean and safe water. Approximately 1 in 5 cases of mortality due to waterborne diseases involve children, and over 1.5 million cases of waterborne disease occur every year. In th...
In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for training. Sec...
Low-carbon pilot policies are essential for the green transformation of resource-based cities, helping them mitigate the “carbon curse” and the “resource curse” while promoting sustainable socio-ecological development. Focusin...
Air quality monitoring (AQM) is key to maintaining healthy air in cities. This is crucial in low- and middle-income countries due to increasing evidence of poor air quality but lack of monitors to consistently collect evaluate air quality data and ef...
Cantonese automatic speech recognition (ASR) faces persistent challenges due to its nine lexical tones, extensive phonological variation, and the scarcity of professionally transcribed corpora. To address these issues, we propose a lightweight and da...
A paradigm shift is required to transform current natural resource management (NRM) in Indonesia’s decision to move into low-carbon development to achieve the greenhouse gas emission target. No study has been conducted to assess whether or not...
The research focuses on the development and evaluation of a legal question–answer system for the Kazakh language, a low-resource and morphologically complex language. Four datasets were compiled from open legal sources—Adilet, Zqai, Gov,...
Deep neural networks (DNNs) have shown a great achievement in acoustic modeling for speech recognition task. Of these networks, convolutional neural network (CNN) is an effective network for representing the local properties of the speech formants. H...
This paper proposes a Tibetan judicial event argument extraction method based on machine reading comprehension (MRC) to address the challenges of data scarcity and insufficient model generalization in low-resource language scenarios. Unlike tradition...
While Large Language Models (LLMs) have significantly advanced various benchmarks in Natural Language Processing (NLP), the challenge of low-resource tasks persists, primarily due to the scarcity of data and difficulties in annotation. This study int...
With the rapid development of Automatic Speech Recognition (ASR) technology, end-to-end speech recognition systems have gained significant attention due to their ability to directly convert raw speech signals into text. However, such systems heavily...
Machine Translation (MT) for low-resource languages, such as Twi, remains a persistent challenge in natural language processing (NLP) due to the scarcity of extensive parallel datasets. Due to their heavy reliance on high-resource data, traditional m...
In this paper, a contrastive learning approach for morphological disambiguation (MD) using large language models (LLMs) is presented. A contrastive loss function is introduced for training the approach, which reduces the distance between the correct...
The pre-training fine-tuning mode has been shown to be effective for low resource neural machine translation. In this mode, pre-training models trained on monolingual data are used to initiate translation models to transfer knowledge from monolingual...
Bacterial identification is challenging in low-resource settings (LRS). We evaluated the MicroScan identification panels (Beckman Coulter, Brea, CA, USA) as part of Médecins Sans Frontières’ Mini-lab Project. The MicroScan Dried Overnight Positive ID...
of 334