Related papers: WSRGlow: A Glow-based Waveform Generative Model fo…
Spoken language understanding (SLU) system usually consists of various pipeline components, where each component heavily relies on the results of its upstream ones. For example, Intent detection (ID), and slot filling (SF) require its…
Inspired by the recent progress in self-supervised learning for computer vision, in this paper we introduce DeLoRes, a new general-purpose audio representation learning approach. Our main objective is to make our network learn…
The application of generative adversarial networks (GANs) has recently advanced speech super-resolution (SR) based on intermediate representations like mel-spectrograms. However, existing SR methods that typically rely on independently…
Single Image Super-resolution (SISR) produces high-resolution images with fine spatial resolutions from aremotely sensed image with low spatial resolution. Recently, deep learning and generative adversarial networks(GANs) have made…
Video super-resolution (SR) aims at generating a sequence of high-resolution (HR) frames with plausible and temporally consistent details from their low-resolution (LR) counterparts. The key challenge for video SR lies in the effective…
We investigate the potential of stochastic neural networks for learning effective waveform-based acoustic models. The waveform-based setting, inherent to fully end-to-end speech recognition systems, is motivated by several comparative…
Automatic speech recognition (ASR) has gained remarkable successes thanks to recent advances of deep learning, but it usually degrades significantly under real-world noisy conditions. Recent works introduce speech enhancement (SE) as…
There have been several successful deep learning models that perform audio super-resolution. Many of these approaches involve using preprocessed feature extraction which requires a lot of domain-specific signal processing knowledge to…
This paper introduces a novel reference-free (RF) audio quality metric called the RF-Generative Machine Listener (RF-GML), designed to evaluate coded mono, stereo, and binaural audio at a 48 kHz sample rate. RF-GML leverages transfer…
Diffusion models have achieved state-of-the-art image generation. However, the random Gaussian noise used to start the diffusion process influences the final output, causing variations in image quality and prompt adherence. Existing…
Diffusion models can learn rich representations during data generation, showing potential for Self-Supervised Learning (SSL), but they face a trade-off between generative quality and discriminative performance. Their iterative sampling also…
Self-supervised learning (SSL) is a powerful paradigm for learning from unlabeled time-series data. However, popular methods such as masked autoencoders (MAEs) rely on reconstructing inputs from a fixed, predetermined masking ratio. Instead…
Most current speech enhancement models use spectrogram features that require an expensive transformation and result in phase information loss. Previous work has overcome these issues by using convolutional networks to learn long-range…
Deep learning has become a de facto method of choice for speech enhancement tasks with significant improvements in speech quality. However, real-time processing with reduced size and computations for low-power edge devices drastically…
The effective utilization of observational data is frequently hindered by insufficient resolution. To address this problem, we present a new spatio-temporal super-resolution (STSR) model, called InWaveSR. It is built on a deep learning…
Diffusion models have demonstrated remarkable success in generative tasks, including audio super-resolution (SR). In many applications like movie post-production and album mastering, substantial computational budgets are available for…
In this paper, we propose LSRNA, a novel framework for higher-resolution (exceeding 1K) image generation using diffusion models by leveraging super-resolution directly in the latent space. Existing diffusion models struggle with scaling…
High-resolution (HR) information of fluid flows, although preferable, is usually less accessible due to limited computational or experimental resources. In many cases, fluid data are generally sparse, incomplete, and possibly noisy. How to…
Deep matching models aim to facilitate search engines retrieving more relevant documents by mapping queries and documents into semantic vectors in the first-stage retrieval. When leveraging BERT as the deep matching model, the attention…
The visibility of real-world images is often limited by both low-light and low-resolution, however, these issues are only addressed in the literature through Low-Light Enhancement (LLE) and Super- Resolution (SR) methods. Admittedly, a…