Search Results for author:
Found 5 papers, 3 papers with code
UnDiff: Unsupervised Voice Restoration with Unconditional Diffusion Model
Being once trained for speech waveform generation in an unconditional manner, it can be adapted to different tasks including degradation inversion, neural vocoding, and source separation.
Iterative autoregression: a novel trick to improve your low-latency speech enhancement model
Streaming models are an essential component of real-time speech enhancement tools.
FFC-SE: Fast Fourier Convolution for Speech Enhancement
The FFC operator allows employing large receptive field operations within early layers of the neural network.
HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement
Generative adversarial networks have recently demonstrated outstanding performance in neural vocoding outperforming best autoregressive and flow-based models.
Quantization of Generative Adversarial Networks for Efficient Inference: a Methodological Study
While quantization is well established for discriminative models, the performance of modern quantization techniques in application to GANs remains unclear.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
