Academic achievements

This study explores personalized Mandarin ASR for the speech impaired. Sentence and short phrase tasks selected from the VoiceBank-2023 corpus are examined for amyotrophic lat-eral sclerosis and esophageal-speech speakers. Unadapted speaker-independent ASR model is trained with the NER-Pro corpus to serve as a pretrained model for the follow-up speaker-independent and dependent models fine-tuned with the CDSD and VoiceBank-2023 corpora. Several fine-tuning strategies are investigated. Experimental results show that the adapted speaker-dependent models attain average character error rates (CERs) ranging from 6.8% (normal) to 11.9% (mod-erate dysarthria) and 5.9% (normal) to 12.9% (moderate) for sentence and short phrase tasks, respectively. Last, we have implemented the fine-tuning strategies on a large corpus of a hereditary spastic paraplegia patient to evaluate frequently used sentence tasks under open-set and close-set conditions, resulting in CERs of 10.8% and 3.8%, respectively.

‍

The Truku language is one of the minority Indigenous languages of Taiwan. This paper presents the development of Taiwan’s first-ever Truku language text-to-speech (TTS) model, utilizing over 8 hours of high-quality audio recordings collected from professional male and female Truku speakers. The recordings were processed using VITS2 (Variational Inference for Text-to-Speech) technology to train a robust Truku-TTS model, which can accurately synthesize natural sounding spoken language from written Truku text. To facilitate the model training, we leveraged the computational power of the National Center for High-performance Computing (NCHC), we were able to significantly enhance model training efficiency and performance. Furthermore, we integrated Optical Character Recognition (OCR) technology into the Truku-TTS model workflow, allowing us to convert printed Truku language books into digital audiobooks. This innovative approach not only preserves Truku language but also broadens its accessibility, allowing a wider audience to engage with Truku content. The Truku-TTS model contributes substantially to ongoing efforts to preserve and revitalize Truku languages and provides a crucial tool for cultural and linguistic education. Our methodology and results demostrate a framework that can effectively preserve Truku language materials, enhance Truku language promotion services, and further extend these efforts ro cover all 16 Indigeous tribes comprising 42 dialects in Taiwan, achieving the goal of revitalizing and sustaining Indigenous languages.

‍

Frailty in older adults is caused by functional declines that result in unstable gait. This study analyzed gait in 24 frail and 22 non-frail older adults using acceleration and angular velocity signals from a wireless tri-axial inertial measurement unit (IMU). After noise was removed through Savitzky-Golay and Butterworth filters, gait features correlated with frailty were proposed and evaluated through normality tests and statistical analysis. To evaluate the frailty of older adults based on significant gait features derived from statistical analysis, the primary accuracy achieved is roughly around 84–89 % in k-nearest neighbor, support vector machine, and random forest models. To provide clinicians with a good tool for monitoring frailty and support preventive healthcare and aging-in-place strategies, we propose a gait-based detection system with an optimal feature extraction scheme that can exhaustively enumerate and evaluate potential parameters for optimal performance. This system significantly improved classification metrics (nearly all >95 %) with lower sensitivity and specificity and achieved 96 % accuracy with a portable, low-cost system that uses only one minute of walking data. These findings demonstrate that IMU-based gait analysis improves objectivity and accuracy in frailty classification. The optimal feature extraction scheme further refines performance, offering a scalable and time-efficient solution for community-based frailty detection. This approach highlights the potential of wearable sensors in improving geriatric health assessments.

‍

As the global average age increases and the number of patients with frailty and degenerative joint diseases like arthritis continues to rise, rehabilitation clinics often experience congestion due to the increasing demand for rehabilitation. Promoting proactive exercise among older adults and increasing their adherence can effectively reduce the prevalence of frailty. However, attracting users to regularly engage with and ensuring an easily usable operation flow and interface design will be crucial as an effective technological solution to improve the health issues of the elderly.This study proposes an upper limb game training software with a nostalgic retro theme, the game utilizes wearable devices with sEMG and g-sensor sensors for game interaction. Older adults will actually operate the game and complete the SUS usability questionnaire. The SUS questionnaire results for this game received an A-level usability rating. Based on the SUS scores, the upper limb game training software proposed in this study has development potential. The software is easy for the older adult population to engage with, regardless of age or past rehabilitation experience, and they have the willingness to continue using it.

‍

This study aims to explore the application of digital muscle strength testing systems in day care centers and analyze their adaptability and benefits for the elderly population. With the increasing global aging trend, sarcopenia has become a significant health issue, severely impacting the daily functioning and long-term care needs of older adults. Smart sensing technologies provide innovative solutions for long-term care facilities, enabling effective muscle strength and functional movement monitoring in elderly individuals. This study employs a mixed-methods approach, combining quantitative data analysis and qualitative interviews to assess the usability and acceptability of the intelligent testing system in long-term care institutions. The results indicate that the system performs well in muscle strength testing for older adults, with completion rates of 94.87% for the Dorsiflexion Ability and 92.31% for the 3M Gait Test. ANOVA analysis revealed no significant differences between the different stages of testing (3M Gait Test: F = 0.62, p = 0.54; 5 Times Sit-to-Stand Test: F = 0.62, p = 0.54). However, the results show a trend of “improvement at the mid-test and decline at the post-test,” highlighting potential challenges in the long-term implementation of the system in institutions. The qualitative analysis suggests that caregivers have a high level of acceptance of the system but also indicate areas for optimization in adapting the system to the “group nature” of the institution. This study provides valuable insights for optimizing and promoting digital muscle strength testing systems in long-term care facilities.

‍

The research involved the development of a fuzzy inference system (FIS) to predict grip strength through the analysis of sEMG signals. Fuzzy rules were generated using fuzzy c-means (FCM) clustering. In an experiment focused on lifting motions and including nine participants, the FIS demonstrated promising results. Specifically, in the non-weight condition, the FIS achieved a Mean Squared Error (MSE) of 0.1246 and an R-squared value of 0.3357 for grip strength prediction. However, when an 11-lb weight load was introduced, the accuracy of the FIS dropped significantly, leading to less reliable predictions. This was reflected in an increased MSE of 0.1804 and a reduced R-squared value of 0.0379. These outcomes underscore the potential of wearable sEMG devices coupled with a fuzzy inference system for grip strength prediction. The research also highlights the need for further research in this evolving field.

‍

Sarcopenia, gait disturbance, and intradialytic hypotension are among the various factors that contribute to fall risk. This study aimed to investigate the relationship between risk of sarcopenia, hemodialysis (HD) session, and long-term fall risk in older end-stage kidney disease (ESKD) patients by analyzing their spatiotemporal gait characteristics.

‍

With the increasing elderly population, the number of individuals afflicted with dementia is also rising year by year. Apart from causing cognitive impairments, dementia also leads to a decline in hand grip strength, thereby impacting the daily lives of patients. Hence, this study endeavors to design and develop a novel wearable sensing device that integrates sEMG technology. It aims to accurately detect and train hand grip strength in the elderly population with dementia, with the ultimate goal of effectively preventing the onset of dementia.

The prevalence of degenerative diseases among older adults has been increasing, leading to a decline in their ability to perform daily activities. Frailty and dementia are associated, and hand strength training plays a crucial role in dementia prevention. Existing training products do not consider the hand size of older adults. Thus, this study focuses on developing a wearable hand strength training device specifically for older adults. The design incorporates universal design principles to enhance usability. Through subjective feedback obtained using the System Usability Scale (SUS) and interviews, the results show that the glove assistive device designed for older adults significantly improves comfort during training. Participants expressed a willingness to use this device for extended periods. Future designs should integrate diverse muscle strength training movements based on older adults' hand size, offering more options for independent home-based training, and indirectly reducing the occurrence of dementia.

‍

Services of personalized TTS systems for the Mandarin-speaking speech impaired are rarely mentioned. Taiwan started the VoiceBanking project in 2020, aiming to build a complete set of services to deliver personalized Mandarin TTS systems to amyotrophic lateral sclerosis patients. This paper reports the corpus design, corpus recording, data purging and correction for the corpus, and evaluations of the developed personalized TTS systems, for the VoiceBanking project. The developed corpus is named after the VoiceBank-2023 speech corpus because of its release year. The corpus contains 29.78 hours of utterances with prompts of short paragraphs and common phrases spoken by 111 native Mandarin speakers. The corpus is labeled with information about gender, degree of speech impairment, types of users, transcription, SNRs, and speaking rates. The VoiceBank-2023 is available by request for non-commercial use and welcomes all parties to join the VoiceBanking project to improve the services for the speech impaired.

Speech-to-speech translation (S2ST), particularly in the context of low-resource languages, plays a vital role in facilitating global communication. However, comprehensive research in this emerging field is lacking, especially concerning translation without the use of text. The objective of this study is to bridge the gap by conducting a systematic review of existing literature on S2ST for low-resource languages. We discovered 455 articles by searching the Scopus, IEEE Xplore, and ACM Digital Library databases, focusing on identifying research trends. The results highlight significant topics covered in the literature, marking a transition from traditional neural network methodologies to advanced transformer-based models. Our findings provide a robust overview of the S2ST landscape, identifying challenges and potential solutions for future research, particularly regarding the application of this technology in low-resource settings. The research contribution of this study is the insights gleaned will benefit academics and professionals seeking a comprehensive understanding of S2ST for low-resource languages.

對高齡者與身心障礙者來說，要取得每日營養膳食以維持基本的身體健康，是一件不容易且有風險的事。研究指出，高齡者與身心障礙者的營養攝取、健康狀況和社會連結間存在明顯的關係。經濟困難或獨自居住的高齡者與身心障礙者，有較高機率難以獲取足夠的食物與營養來維持健康的生活，而營養不良也增加了受傷、生病和提早入院的風險；在這樣的狀況下，高齡者與身心障礙者更容易被社會孤立，及面臨經濟惡性循環的困境，連帶心理健康亦會受到影響（Wright et al., 2015）。

我國內政部於 1993 年起，輔導各縣市地方政府辦理送餐服務，以協助高齡者克服烹煮食物及購物之不便，享有營養均衡的食物（何道珍等人，2003）。送餐服務兼顧健康照顧與社會服務，在提供均衡飲食的同時，也提供訪視問安、資源連結、觀察生活條件、日常問題解決、關懷網絡媒合等服務（潘承揚，2013；Thomas et al., 2020）。研究發現，居家送餐服務（Home-delivered Meal Services）是協助高齡者與身心障礙者能成功在地安老、保持獨立、減少孤獨與住院率、提升心理健康與幸福感的重要措施（Thomas et al., 2020; Westcott et al., 2022; Wright et al., 2015; Yanagisawa & Sakakibara, 2008）。

不同於 Ubereats 或者 Foodpanda 等商業送餐，居家送餐服務至少需整合營養膳食、交通運輸與社會工作（陳燕禎等人， 2005），是一項高複雜度與高整合度的任務。其涉及的相關工作細項繁多，包括：採購、倉儲、膳食烹調、送餐交通與接駁、財務與收支規劃管理、資訊系統維護……等。參與其中的工作角色也不少，包括：採購人員、送餐員、社工、廚工、財會人員、管理人員、客服人員……等等。此外，需維運管理的資源設施亦相當多，包括：大宗食材、中央廚房、車輛、工作地點、接駁據點、辦公環境……等等。送餐服務除需接受一般營運的要求，例如，勞動基準、食品安全、環境保護、消防、交通、建築等規範外，還需符合各式法令規章的檢視，例如，《老人福利法》、《身心障礙者權益保障法》、《長期照顧十年計畫》、社會工作倫理、志工倫理等等。因此，投入服務之服務機構需具備管理資源設施、整合工作任務與服務人員、以及符合各項法令規定等能力才能達成送餐任務。

參與居家送餐服務的機構多為民間社福組織或社區型單位，服務的地區擴及路程遙遠的偏鄉，加以複雜度高、整合度高，需投入的個案管理、訂餐與製餐、及相關行政業務的人力成本也高，因此如何透過數位化或數位優化來提升服務效能，是近年來參與送餐服務的社福組織或民間機構思考的重點。

‍