Abstract: In this paper, we propose an audio spectrogram transformer (AST) for sequential inference and evaluate its real- time performance. ASTs are pre-trained in a self-supervised manner, such as ...

This project implements a comprehensive machine learning solution for classifying respiratory diseases (Asthma and COPD) from medical sound recordings. The system employs multiple approaches including ...

OpenAI will reportedly base the model on a new architecture. The company’s current flagship real-time audio model, ...

Explore some favorite visual stories of designers, developers and art directors from The Washington Post’s Design, Graphics and Opinions teams.

Now, the researchers at Yellowstone National Park want to learn wolf language beyond what has been fed to us through ...

Fish have been known to make sounds for over two millennia, yet much of this underwater world has remained acoustically ...

Music is an essential part of human culture, but automatically classifying songs into genres is a challenging problem for computers. With the explosion of digital music libraries, manual tagging is ...

As AI Music Tools Proliferate, Detection Technologies and Industry Responses EvolveThe music industry faces an unprecedented ...

Deepfake scams are increasing at an alarming rate, surging over 520% in 2025 alone. AI-generated voices and faces are tricking people into transferring millions of dollars, often under the guise of ...

Merlin has been trained to identify the songs of more than 1,300 bird species around the world ...

If bowhead whales produce particularly varied and diverse calls in one area, it is very likely that the area is a breeding ground. The species occurs exclusively in the Arctic Ocean and is therefore ...

Whales breed in specific areas deep beneath the Arctic Circle ice, reveals new research. Scientists used state of the art AI ...