Audio-Text Foundation Models (ATMs) fail catastrophically under severe acoustic noise, yet existing adaptation strategies either rely on gradient-based Test-Time Adaptation (TTA), which reinforces...
<p><strong>Tác giả:</strong> Ashish Anand Shukla, Rini Smita Thakur, Aryan Das, Vinod K Kurmi</p>
<p>Audio-Text Foundation Models (ATMs) fail catastrophically under severe acoustic noise, yet existing adaptation strategies either rely on gradient-based Test-Time Adaptation (TTA), which reinforces noise rather than signal, or on prompt tuning that requires privileged noise annotations unavailable at inference. We address these failures with PRISM (Prototype-Rectified Iterative Self-supervised Manifold Denoising), a training-free, source-free TTA framework grounded in the Affine Noise Hypothes...</p>
<p>📄 DOI: <a href="https://doi.org/https://doi.org/10.1145/3799682.3840694" target="_blank" rel="noopener">https://doi.org/10.1145/3799682.3840694</a></p>
<p>📖 <a href="https://doi.org/https://doi.org/10.1145/3799682.3840694" target="_blank" rel="noopener">Xem bài báo đầy đủ</a></p>
Bài viết được biên soạn lại bởi LIFVietnam. Nguồn tham khảo: OpenAlex
