GitHub

DisCoder: High-Fidelity Music Vocoder Using Neural Audio Codecs

DisCoder is a neural vocoder that leverages a generative adversarial encoder-decoder architecture informed by a neural audio codec to reconstruct high-fidelity 44.1 kHz audio from mel spectrograms.
BBC

The fetch-decode-execute cycle

The fetch-decode-execute cycle is followed by a processor to process an instruction. The cycle consists of several stages. Depending on the type of instruction, additional steps may be taken: If the ...
IEEE

Model-Guided Deep Learning for Line Segment Detection in Time–Frequency Spectrograms of an Ocean Waveguide

Abstract: The application of machine learning in underwater acoustics is often limited by the lack of high-quality data. One method to avoid this data issue is to use modeled data to train a machine ...
IEEE

SMMA-Net: An Audio Clue-Based Target Speaker Extraction Network with Spectrogram Matching and Mutual Attention

Abstract: We propose a deep neural network with spectrogram matching and mutual attention (SMMA-Net) for audio clue-based target speaker extraction (TSE). To effectively use the auxiliary speech, we ...
GitHub

Beyond Spectrograms: Rethinking Audio Classification from EnCodec’s Latent Space

All the datasets must be located in the datasets folder. This folder should contain the following subfolders after downloading the datasets: GTZAN Speech_Music: Contains the GTZAN Speech Music dataset ...