Related papers: Spark Deficient Gabor Frames for Inverse Problems
The advent of Transformer-based models has surpassed the barriers of text. When working with speech, we must face a problem: the sequence length of an audio input is not suitable for the Transformer. To bypass this problem, a usual approach…
While deep convolutional architectures have achieved remarkable results in a gamut of supervised applications dealing with images and speech, recent works show that deep untrained non-convolutional architectures can also outperform…
One of the major open problems in computer vision is detection of features in visually impaired images. In this paper, we describe a potential solution using Phase Stretch Transform, a new computational approach for image analysis, edge…
Transformer-based models generate hidden states that are difficult to interpret. In this work, we analyze hidden states and modify them at inference, with a focus on motion forecasting. We use linear probing to analyze whether interpretable…
The Shack-Hartmann wavefront sensor is widely used to measure aberrations induced by atmospheric turbulence in adaptive optics systems. However if there exists strong atmospheric turbulence or the brightness of guide stars is low, the…
This paper presents a new voice conversion (VC) framework capable of dealing with both additive noise and reverberation, and its performance evaluation. There have been studied some VC researches focusing on real-world circumstances where…
Preserving the linguistic content of input speech is essential during voice conversion (VC). The star generative adversarial network-based VC method (StarGAN-VC) is a recently developed method that allows non-parallel many-to-many VC.…
Speaker verification (SV) systems using deep neural network embeddings, so-called the x-vector systems, are becoming popular due to its good performance superior to the i-vector systems. The fusion of these systems provides improved…
Children speech recognition is indispensable but challenging due to the diversity of children's speech. In this paper, we propose a filter-based discriminative autoencoder for acoustic modeling. To filter out the influence of various…
The signal half of an entangled twin-beam, generated using spontaneous parametric downconversion, interrogates a region of space that is suspected of containing a target, and has high loss and high (entanglement-breaking) background noise.…
In this paper, we propose an extension to Longformer Encoder-Decoder, a popular sparse transformer architecture. One common challenge with sparse transformers is that they can struggle with encoding of long range context, such as…
Denoising diffusion probabilistic models have recently received much research attention since they outperform alternative approaches, such as GANs, and currently provide state-of-the-art generative performance. The superior performance of…
For a window $g\in L^2(\mathbb{R})$, the subset of all lattice parameters $(a, b)\in \mathbb{R}^2_+$ such that $\mathcal{G}(g,a,b)=\{e^{2\pi ib m\cdot}g(\cdot-a k) : k, m\in\mathbb{Z}\}$ forms a frame for $L^2(\mathbb{R})$ is known as the…
We present a sparse Gauss-Newton solver for accelerated sensitivity analysis with applications to a wide range of equilibrium-constrained optimization problems. Dense Gauss-Newton solvers have shown promising convergence rates for inverse…
This paper introduces an approach, named DFormer, for universal image segmentation. The proposed DFormer views universal image segmentation task as a denoising process using a diffusion model. DFormer first adds various levels of Gaussian…
Swin-Transformer has demonstrated remarkable success in computer vision by leveraging its hierarchical feature representation based on Transformer. In speech signals, emotional information is distributed across different scales of speech…
We present a sensor-agnostic spectral transformer as the basis for spectral foundation models. To that end, we introduce a Universal Spectral Representation (USR) that leverages sensor meta-data, such as sensing kernel specifications and…
Transformer-based end-to-end speech recognition has achieved great success. However, the large footprint and computational overhead make it difficult to deploy these models in some real-world applications. Model compression techniques can…
The Transformer architecture has revolutionized the field of deep learning over the past several years in diverse areas, including natural language processing, code generation, image recognition, time series forecasting, etc. We propose to…
As the first step in automated natural language processing, representing words and sentences is of central importance and has attracted significant research attention. Different approaches, from the early one-hot and bag-of-words…