US scrambles to stop Internet users re-creating dead pilots’ voices

Pilots’ voices from the last seconds of a fatal cargo plane crash have been re-created by Internet sleuths using software and AI tools. The spread of reconstructed audio recordings has prompted a US ...
IEEE

Drill Fault Diagnosis Based on the Scalogram and Mel Spectrogram of Sound Signals Using Artificial Intelligence

Abstract: In industry, the ability to detect damage or abnormal functioning in machinery is very important. However, manual detection of machine fault sound is economically inefficient and ...
Phys.org

What can singing mice say about human speech?

(b) Example spectrogram of singing mice (top) and lab mice (bottom) vocalizations during male-female social interaction. Orange and blue colored bars mark the duration of each vocalization for the two ...
Phys.org

NASA's MAVEN detects first evidence of lightning-like activity on Mars

While sifting through the extensive data collected by NASA's Mars Atmosphere and Volatile Evolution (MAVEN) spacecraft over the last decade, scientists discovered a familiar type of electromagnetic ...
GitHub

Masked Spectrogram Modeling using Masked Autoencoders (MSM-MAE)

🎉 The successor to this repository, Masked Modeling Duo (M2D), is now available. If you are starting a new project, please use M2D instead of this repository. The table below compares EVAR benchmark ...
Nature

Automated detection of wolf howls using audio spectrogram transformers

The grey wolf (Canis lupus) is a pivotal species for ecological studies. As a key participant in ecosystem processes, it also serves as a model for investigating social structure formation and ...
National Audubon Society

Start Using Spectrograms to ’Read’ Bird Songs and Calls

Editor’s Note: There's a lot to look forward to in spring, including the welcomed hullabaloo of birdsong. The sheer volume of songs and calls can often feel overwhelming for birders, but these sounds ...
EurekAlert!

A ‘copycat’ in animal kingdom: Chinese blackbirds mimic human-made sounds

Example spectrograms showing the electric moped sounds and the imitations produced by Chinese Blackbirds. (A)–(B) Three examples of locking sound, unlocking sound, and alarms from three brands of ...
Nature

Decoding speech perception from non-invasive brain recordings

Decoding speech from brain activity is a long-awaited goal in both healthcare and neuroscience. Invasive devices have recently led to major milestones in this regard: deep-learning algorithms trained ...
IEEE

Versatile Time-Frequency Representations Realized by Convex Penalty on Magnitude Spectrogram

Abstract: Sparse time-frequency (T-F) representations have been an important research topic for more than several decades. Among them, optimization-based methods (in particular, extensions of basis ...
TechCrunch

Try ‘Riffusion,’ an AI model that composes music by visualizing it

AI-generated music is already an innovative enough concept, but Riffusion takes it to another level with a clever, weird approach that produces weird and compelling music using not audio but images of ...