الملخص
تمت ترجمة أجزاء من هذه الصفحة آلياً وقد تحتوي على أخطاء.
Audio is increasingly used for human activity recognition (HAR) because it captures object interactions, environmental events, and contextual cues in everyday environments. High-resolution (HR) audio provides rich acoustic information for model development but incurs substantial energy and storage costs and may expose sensitive speech content. Low-resolution (LR) audio offers a more privacy-preserving and resource-efficient alternative for deployment, but reduced sampling rates can remove acoustic cues essential for activity recognition, leading to significant performance degradation. We formulate this training-deployment mismatch as sensor-resolution privileged learning, in which HR audio is available during training, while inference relies exclusively on LR audio. We propose RAST, a resolution-aware transfer framework that compresses HR teacher representations by preserving token-level information and neighborhood structure before performing localized HR-LR alignment. Experiments on the SAMoSA and AudioIMU datasets show that RAST consistently outperforms LR-only training and direct teacher-transfer baselines, improving LR-only recognition by up to approximately 7.8% while requiring only LR audio at inference.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Park, J. H., Gudur, G. K., Shen, Y., Liang, D., & Thomaz, E. (2026). RAST: نقل البنية المميزة المدرك للدقة لتمييز نشاط الصوت منخفض الدقة. https://omanscience.com/ar/articles/rast-resolution-aware-privileged-structure-transfer-for-low-resolution-audio-activity-recognition
MLA 9
Park, Ji Hwan, et al. "RAST: نقل البنية المميزة المدرك للدقة لتمييز نشاط الصوت منخفض الدقة." https://omanscience.com/ar/articles/rast-resolution-aware-privileged-structure-transfer-for-low-resolution-audio-activity-recognition.
شيكاغو (المؤلف–التاريخ)
Park, Ji Hwan, Gautham Krishna Gudur, Yufei Shen, Dawei Liang, and Edison Thomaz. 2026. "RAST: نقل البنية المميزة المدرك للدقة لتمييز نشاط الصوت منخفض الدقة." https://omanscience.com/ar/articles/rast-resolution-aware-privileged-structure-transfer-for-low-resolution-audio-activity-recognition.
هارفارد
Park, J. H., Gudur, G. K., Shen, Y., Liang, D. and Thomaz, E. (2026) 'RAST: نقل البنية المميزة المدرك للدقة لتمييز نشاط الصوت منخفض الدقة', Available at: https://omanscience.com/ar/articles/rast-resolution-aware-privileged-structure-transfer-for-low-resolution-audio-activity-recognition.
فانكوفر
Park JH, Gudur GK, Shen Y, Liang D, Thomaz E. RAST: نقل البنية المميزة المدرك للدقة لتمييز نشاط الصوت منخفض الدقة. https://omanscience.com/ar/articles/rast-resolution-aware-privileged-structure-transfer-for-low-resolution-audio-activity-recognition
IEEE
J. H. Park, G. K. Gudur, Y. Shen, D. Liang, and E. Thomaz, "RAST: نقل البنية المميزة المدرك للدقة لتمييز نشاط الصوت منخفض الدقة," https://omanscience.com/ar/articles/rast-resolution-aware-privileged-structure-transfer-for-low-resolution-audio-activity-recognition.