Traini Raises $7.5 Million to Build Pet Emotional Intelligence

Palo Alto–based pet emotional intelligence startup Traini has announced the completion of a $7.5 million funding round, ...
IEEE

Spectrogram-Based Analysis and Detection of Deepfake Audio Using Enhanced DCGANs for Secure Content Distribution

Abstract: While DCGAN as deep learning model utilizing spectrogram, allows for detection of deepfake audio, it is prone to overfitting which affects its ability to discriminate between real and fake ...
GitHub

Python script to embed visual watermarks directly into audio file spectrograms using STFT.

This tool allows you to take an image and embed it as a visual pattern within the spectrogram of an audio file. The process involves performing a Short-Time Fourier Transform (STFT) on the audio, ...
IEEE

Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers

Abstract: Parameter-efficient transfer learning (PETL) methods have emerged as a solid alternative to the standard full fine-tuning approach. They only train a few extra parameters for each downstream ...
GitHub

yoyolicoris/music-spectrogram-diffusion-pytorch

An unofficial PyTorch implementation of the paper Multi-instrument Music Synthesis with Spectrogram Diffusion, adapted from official codebase. We aim to increase the reproducibility of their work by ...