Modulate launches AI music detection as synthetic tracks flood streaming

Voice artificial intelligence company Modulate Inc. today launched a tool that flags AI-generated music straight from the ...
IEEE

Audio Sentiment Analysis with Spectrogram Representations and Transformer Models

Abstract: Recent advancements in the domain of computer vision have enabled the analysis of audio spectrograms. In this paper, we present a novel approach that leverages spectrogram representations ...
IEEE

Contrastive Audio Spectrogram Transformer for Robust Recognition of Environmental Acoustic Signals

Abstract: In recent years, environmental sound classification has become an essential component in intelligent urban monitoring systems, smart infrastructure, and public noise analysis. However, this ...
GitHub

Multimodal Human Action Recognition for Ubiquitous Systems

A TensorFlow multimodal HAR system fusing skeleton and audio via 4-head Cross-Attention. ResNet-50 processes 31-channel spatiotemporal heatmaps; ConvNeXt-Tiny encodes log-Mel+Δ+Δ² spectrograms.
NPR

The NTSB tries to keep cockpit audio recordings private. AI is making that harder

WASHINGTON — What began as an inquiry into a mysterious sound in the background of an airplane cockpit voice recording escalated into an unexpected challenge for the nation's top safety investigators.