Related papers: Generative De-Quantization for Neural Speech Codec…

Although deep convolutional neural network has been proved to efficiently eliminate coding artifacts caused by the coarse quantization of traditional codec, it's difficult to train any neural network in front of the encoder for gradient's…

We present a deep neural network to reduce coherent noise in three-dimensional quantitative phase imaging. Inspired by the cycle generative adversarial network, the denoising network was trained to learn a transform between two image…

Most existing image compression approaches perform transform coding in the pixel space to reduce its spatial redundancy. However, they encounter difficulties in achieving both high-realism and high-fidelity at low bitrate, as the…

Flow matching and diffusion models have shown impressive results in text-to-image generation, producing photorealistic images through an iterative denoising process. A common strategy to speed up synthesis is to perform early denoising at…

End-to-end learning models have demonstrated a remarkable capability in performing speech segregation. Despite their wide-scope of real-world applications, little is known about the mechanisms they employ to group and consequently segregate…

Generative modeling aims to generate new data samples that resemble a given dataset, with diffusion models recently becoming the most popular generative model. One of the main challenges of diffusion models is solving the problem in the…

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…

Image codecs are typically optimized to trade-off bitrate \vs distortion metrics. At low bitrates, this leads to compression artefacts which are easily perceptible, even when training with perceptual or adversarial losses. To improve image…

We introduce a state-of-the-art real-time, high-fidelity, audio codec leveraging neural networks. It consists in a streaming encoder-decoder architecture with quantized latent space trained in an end-to-end fashion. We simplify and speed-up…

Audio codecs are a critical component of modern speech generation systems. This paper introduces a low-bitrate, multi-scale residual codec that encodes speech into four distinct streams: semantic, timbre, prosody, and residual. This…

Denoising Diffusion Probabilistic Models have shown extraordinary ability on various generative tasks. However, their slow inference speed renders them impractical in speech synthesis. This paper proposes a linear diffusion model (LinDiff)…

We propose a Deep Texture Encoding Network (Deep-TEN) with a novel Encoding Layer integrated on top of convolutional layers, which ports the entire dictionary learning and encoding pipeline into a single model. Current methods build from…

Discrete diffusion models are a powerful, emerging paradigm for code generation. They construct programs through iterative refinement of partially corrupted token sequences and enable parallel token refinement. Importantly, this paradigm…

We present a scalable and efficient neural waveform coding system for speech compression. We formulate the speech coding problem as an autoencoding task, where a convolutional neural network (CNN) performs encoding and decoding as a neural…

Speech-to-face generation is an intriguing area of research that focuses on generating realistic facial images based on a speaker's audio speech. However, state-of-the-art methods employing GAN-based architectures lack stability and cannot…

Autoregressive speech synthesis often adopts a left-to-right order, yet generation order is a modelling choice. We investigate decoding order through masked diffusion framework, which progressively unmasks positions and allows arbitrary…

Diffusion models are emerging models that generate images by iteratively denoising random Gaussian noise using deep neural networks. These models typically exhibit high computational and memory demands, necessitating effective post-training…

This paper presents an end-to-end text-to-speech system with low latency on a CPU, suitable for real-time applications. The system is composed of an autoregressive attention-based sequence-to-sequence acoustic model and the LPCNet vocoder…

In speech enhancement, complex neural network has shown promising performance due to their effectiveness in processing complex-valued spectrum. Most of the recent speech enhancement approaches mainly focus on wide-band signal with a…

Recent learning-based lossless image compression methods encode an image in the unit of subimages and achieve comparable performances to conventional non-learning algorithms. However, these methods do not consider the performance drop in…