Detection of Audio Tampering Based on Electric Network Frequency Signal.

The detection of audio tampering plays a crucial role in ensuring the authenticity and integrity of multimedia files. This paper presents a novel approach to identifying tampered audio files by leveraging the unique Electric Network Frequency (ENF) signal, which is inherent to the power grid and serves as a reliable indicator of authenticity. The study begins by establishing a comprehensive Chinese ENF database containing diverse ENF signals extracted from audio files. The proposed methodology involves extracting the ENF signal, applying wavelet decomposition, and utilizing the autoregressive model to train effective classification models. Subsequently, the framework is employed to detect audio tampering and assess the influence of various environmental conditions and recording devices on the ENF signal. Experimental evaluations conducted on our Chinese ENF database demonstrate the efficacy of the proposed method, achieving impressive accuracy rates ranging from 91% to 93%. The results emphasize the significance of ENF-based approaches in enhancing audio file forensics and reaffirm the necessity of adopting reliable tamper detection techniques in multimedia authentication.

Plan and Then Act: The Moderated Moderation Effects of Profession Identity and Action Control for Students at Arts Universities during the Career Development Process.

Preservice teachers at universities of arts have more than 10 years of professional training before admission, but in their senior year, they face the pressure of the graduation exhibition and performances and the teacher certification examination at the same time. This process is dissimilar to that for preservice teachers at general universities. Such a difference, however, has not been taken seriously in the past. In order to avoid burnout, preservice teachers at universities of arts, when they are under the pressure of limited time, may choose to identify with the departments they are more familiar with for their future careers, rather than identifying with their educational program, in order to increase hope for their career and reduce the chance of burnout. In addition, we believe that the use of action control/state control would also show different adaptation situations in the face of pressure. Therefore, this study focuses on the role of profession identity and action control as moderating variables in the process of becoming preservice teachers at arts universities. We recruited 304 art-major preservice teachers to establish a path model to explore their future time perspective and grit, detecting how the mediation of career decision self-efficacy affects learning burnout and career hope. Secondly, we inspected the moderating effect of profession identity and action control on learning burnout and career hope. We found that profession identity moderates the relationships between future time perspective and career decision self-efficacy as well as between career decision self-efficacy and learning burnout, all of which exhibited ordinal interactions. Furthermore, preservice teachers with high decision-making efficacy had lower burnout than those with low efficacy, but the high-efficacy advantage in preservice teachers under state control in reducing burnout would disappear. Lastly, although professional identification was important, action control regulated the relationship between career decision self-efficacy and learning burnout with ordinal interaction; that is, action control could effectively reduce their learning burnout.

Using SincNet for Learning Pathological Voice Disorders.

Deep learning techniques such as convolutional neural networks (CNN) have been successfully applied to identify pathological voices. However, the major disadvantage of using these advanced models is the lack of interpretability in explaining the predicted outcomes. This drawback further introduces a bottleneck for promoting the classification or detection of voice-disorder systems, especially in this pandemic period. In this paper, we proposed using a series of learnable sinc functions to replace the very first layer of a commonly used CNN to develop an explainable SincNet system for classifying or detecting pathological voices. The applied sinc filters, a front-end signal processor in SincNet, are critical for constructing the meaningful layer and are directly used to extract the acoustic features for following networks to generate high-level voice information. We conducted our tests on three different Far Eastern Memorial Hospital voice datasets. From our evaluations, the proposed approach achieves the highest 7%-accuracy and 9%-sensitivity improvements from conventional methods and thus demonstrates superior performance in predicting input pathological waveforms of the SincNet system. More importantly, we intended to give possible explanations between the system output and the first-layer extracted speech features based on our evaluated results.