16 papers with code • 2 benchmarks • 2 datasets

This task has no description! Would you like to contribute one?

Most implemented papers

Detecting the Unexpected via Image Resynthesis

cvlab-epfl/detecting-the-unexpected ICCV 2019

In this paper, we tackle the more realistic scenario where unexpected objects of unknown classes can appear at test time.

Differentiable Time-Frequency Scattering on GPU

cyrusvahidi/kymatio-wavespin 18 Apr 2022

Joint time-frequency scattering (JTFS) is a convolutional operator in the time-frequency domain which extracts spectrotemporal modulations at various rates and scales.

Generative Spoken Language Modeling from Raw Audio

pytorch/fairseq 1 Feb 2021

We introduce Generative Spoken Language Modeling, the task of learning the acoustic and linguistic characteristics of a language from raw audio (no text, no labels), and a set of metrics to automatically evaluate the learned representations at acoustic and linguistic levels for both encoding and generation.

Speech Resynthesis from Discrete Disentangled Self-Supervised Representations

facebookresearch/speech-resynthesis 1 Apr 2021

We propose using self-supervised discrete representations for the task of speech resynthesis.

Unifying Probabilistic Models for Time-Frequency Analysis

wil-j-wil/unifying-prob-time-freq 6 Nov 2018

In audio signal processing, probabilistic time-frequency models have many benefits over their non-probabilistic counterparts.

Coordinate-based Texture Inpainting for Pose-Guided Image Generation

dolorousrtur/coordinate_based_inpainting 28 Nov 2018

Since the input photograph always observes only a part of the surface, we suggest a new inpainting method that completes the texture of the human body.

On Adversarial Mixup Resynthesis

christopher-beckham/amr NeurIPS 2019

In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders.

Parametric Resynthesis with neural vocoders

r9y9/wavenet_vocoder 16 Jun 2019

We propose to utilize the high quality speech generation capability of neural vocoders for noise suppression.

Spectral Processing of COVID-19 Time-Series Data

abstract-theory/Spectral-Processing-COVID-19 13 Aug 2020

The presence of oscillations in aggregated COVID-19 data not only raises questions about the data's accuracy, it hinders understanding of the pandemic.

Dynamical Variational Autoencoders: A Comprehensive Review

XiaoyuBIE1994/DVAE 28 Aug 2020

Recently, a series of papers have presented different extensions of the VAE to process sequential data, which model not only the latent space but also the temporal dependencies within a sequence of data vectors and corresponding latent vectors, relying on recurrent neural networks or state-space models.