Tag
This paper presents a hybrid framework for detecting alarming or distressed student verbal responses by combining a text classifier (content-based) and an audio classifier (prosodic features), aimed at expediting human review in Automated Verbal Response Scoring systems. The approach addresses a safety gap in automated scoring pipelines where at-risk student responses may otherwise go unnoticed.
ArtifactNet is a lightweight neural network framework that detects AI-generated music by analyzing codec-specific artifacts in audio signals, achieving F1=0.9829 on a new 6,183-track benchmark (ArtifactBench) with 49x fewer parameters than competing methods. The approach uses forensic physics principles to extract codec residuals through a bounded-mask UNet and compact CNN, with codec-aware training reducing cross-codec drift by 83%.
Google DeepMind released an updated version of Perch, an AI model for bioacoustic analysis that helps conservationists monitor endangered species through audio data. The new model improves bird species prediction, adapts better to underwater environments, and expands to include mammals, amphibians, and anthropogenic noise, with over 250,000 downloads of the original version.