Abstract: In this study, we explore the use of Vector Quantized Variational Autoencoders (VQ-VAE) for real-time audio spectrogram inpainting, with a focus on minimizing environmental impact. We ...
AudioFingerprint is a production-ready, local audio fingerprinting and song identification system inspired by Shazam and Google Sound Search. It uses spectral peak extraction and combinatorial hashing ...
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 ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback