Kuang-Yow Lian

The rising prevalence of salbutamol residues in food products in recent years presents significant public health risks underscoring urgency for sensitive and reliable detection methods to ensure food safety. Hence, we fabricated an electrochemical sensor for nanomolar-level salbutamol quantification using composite of nickel molybdate integrated zinc-modified montmorillonite K10 ( α NiMoO ₄ /Zn-MMTK10). This composite was immobilized on a screen-printed carbon electrode (SPCE) to form a sensing platform with high electrochemical activity. Electrochemical evaluations demonstrated that α NiMoO ₄ /Zn-MMTK10/SPCE possessed low detection limit of 2.7 nM and broad linear detection range extending from 0.03–37.10 µM. The proposed sensor exhibited superior selectivity and sensitivity toward salbutamol, attributed to α NiMoO ₄ /Zn-MMTK10’s catalytic efficiency. Additionally, sensor showed good reproducibility, repeatability, and long-term stability making it suitable for practical applications. To validate its real-world applicability, sensor was tested on animal-derived food samples including beef jerky, chicken, pork sausage, and cow milk where it achieved high recovery rates ranging from 99.17%–102.16%. These results underscore α NiMoO ₄ /Zn-MMTK10/SPCE sensor’s potential as a robust analytical tool for nanomolar-level quantification of salbutamol in foods.

Nowadays, artificial intelligence (AI)-based voice conversion (VC) models generate high-quality and natural-sounding voices efficiently. While existing studies have focused on detecting voice spoofing attacks, this study explores a proactive approach to safeguard speaker identity from such threats. Attackers can exploit voice biometrics by using either advanced VC techniques or traditional methods. Although zero-shot VC has been applied for source speaker anonymization, it typically fails to protect the identity of the target speaker. To address this gap, we propose a speaker privacy preservation framework that combines zero-shot AutoVC with a multi-target voice frame fusion technique. This method anonymizes the source speaker while also preventing leakage of the target speaker’s identity by blending voice frames from multiple targets. The VCTK public dataset is employed to assess the performance of the proposed model. The average cosine similarity between the original and anonymized voices yielded a result closer to the inter-speaker voice cosine similarity, which is the most suitable benchmark for speaker anonymization. Additionally, speaker identification models trained on original and vocoded data yielded low identification accuracies of 27.4% and 41.2%, respectively. The mean opinion score (MOS) evaluation confirmed that the anonymized voice quality adeptly preserved linguistic content and naturalness. Overall, the proposed method effectively anonymizes both source and target speakers, offering robust protection against voiceprint spoofing.

Deployment of deep learning-based speech processing models for real-world applications on devices with limited processing capacity and memory constraints poses significant challenges. This paper introduces an enhanced deep learning model based on the X-vector architecture, named dilated light-gated recurrent unit in X-vector (DLiGRU-X) to address these challenges specifically for small-footprint keyword spotting (KWS) tasks. The DLiGRU-X model enhances temporal feature extraction with a LiGRU and reduces computational complexity through dilated convolution techniques. The proposed model efficiently learns speech signal characteristics, making it suitable for scenarios with limited hardware resources and can handle an expanded vocabulary size of keyword identification. The proposed model is validated on the Google Speech Command public dataset, and its performance is compared with other recently proposed deep learning models for KWS. The proposed model achieves an excellent trade-off between recognition accuracy and computational complexity, outperforming various advanced keyword spotting models. Notably, despite a reduction in model parameters, DLiGRU-X maintains an accuracy of 97% without significant decline. This model offers greater flexibility compared to previous models, allowing users to adjust and expand the set of targeted vocabulary according to their needs and deploy the model in resource-constrained environments.