Showing 1551 - 1600 of 1951
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
From Unsupervised Machine Translation To Adversarial Text Generation
We present a self-attention based bilingual adversarial text generator (B-GAN) which can learn to generate text from the encoder representation of an unsupervised neural machine translation system. B-GAN is able to generate a distributed latent space repr
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Space Filling Curves For Mri Sampling
A novel class of k-space trajectories for magnetic resonance imaging (MRI) sampling using space filling curves (SFCs) is presented here. More specifically, Peano, Hilbert and Sierpinski curves are used. We propose 1-shot and 4-shot variable density SFCs b
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Beamforming Design For High-Resolution Low-Intensity Focused Ultrasound Neuromodulation
Low-intensity focused ultrasound (LIFU) has been shown to modulate neural activity. Recent experiments suggest potential applications of LIFU stimulation for treating neuropsychiatric disorders like depression and Alzheimer's. The modulation effect is usu
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
State-Space Gaussian Process For Drift Estimation In Stochastic Differential Equations
This paper is concerned with the estimation of unknown drift functions of stochastic differential equations (SDEs) from observations of their sample paths. We propose to formulate this as a non-parametric Gaussian process regression problem and use an It?
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A Multi-Dilation And Multi-Resolution Fully Convolutional Network For Singing Melody Extraction
Each human cognitive function involves bottom-up and top-down processes. Several methods have been proposed for singing melody extraction by emphasizing either the bottom-up or top-down processes. For hearing, the bottom-up processes include spectral and
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Height And Weight Estimation From Unconstrained Images
We address the difficult problem of estimating the weight and height of individuals from pictures taken in completely unconstrained settings. We present a deep learning scheme that relies on simultaneous prediction of human silhouettes and skeletal joints
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A Novel Pruning Approach For Bagging Ensemble Regression Based On Sparse Representation
This work aims to propose an approach for pruning a bagging ensemble regression (BER) model based on sparse representation, which we call sparse representation pruning (SRP). Firstly, a BER model with a specific number of subensembles should be trained. T
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Deriving Compact Feature Representations Via Annealed Contraction
It is common practice to use pretrained image recognition models to compute feature representations for the visual data. The size of the feature representations can have a noticeable impact on the complexity of the models that use these representations, a
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Graph Auto-Encoder For Graph Signal Denoising
Signal denoising is an important problem with a vast literature. Recently, signal denoising on graphs has received a lot of attention due to the increasing use of graph-structured signals. However, well-etablished signal denoising methods do not generaliz
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Deep Audio-Visual Speech Separation With Attention Mechanism
Previous work shows that audio-visual fusion is a practical approach to deal with the speech separation task in the cocktail party problem. In this paper, we explore a better strategy to utilize visual representations with the attention mechanism. Compare
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
The Open Brands Dataset: Unified Brand Detection And Recognition At Scale
Intellectual property protection(IPP) have received more and more attention recently due to the development of the global e-commerce platforms. brand recognition plays a significant role in IPP. Recent studies for brand recognition and detection are based
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Sequential Iot Data Augmentation Using Generative Adversarial Networks
Sequential data in industrial applications can be used to train and evaluate machine learning models (e.g. classifiers). Since gathering representative amounts of data is difficult and time consuming, there is an incentive to generate it from a small grou
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A Connected Auto-Encoders Based Approach For Image Separation With Side Information: With Applications To Art Investigation
X-radiography is a widely used imaging technique in art investigation, whether to investigate the condition of a painting or provide insights into artists? techniques and working methods. In this paper, we propose a new architecture based on the use of 'c
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Pre-Training For Query Rewriting In A Spoken Language Understanding System
Query rewriting (QR) is an increasingly important technique for reducing customer friction resulting from errors in a spoken language understanding pipeline originating from various sources such as speech recognition errors, language understanding errors
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Learning Data Representation And Emotion Assessment From Physiological Data
Aiming at a deeper understanding of human emotional states, we explore deep learning techniques for the analysis of physiological data. In this work, two-channel pre-frontal raw electroencephalography and photoplethysmography signals of 25 subjects were c
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Weighted Speech Distortion Losses For Neural-Network-Based Real-Time Speech Enhancement
This paper investigates several aspects of training a RNN (recurrent neural network) that impact the objective and subjective quality of enhanced speech for real-time single-channel speech enhancement. Specifically, we focus on a RNN that enhances short-t
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Effective Wavenet Adaptation For Voice Conversion With Limited Data
WaveNet has shown its great potential as a direct conversion model in voice conversion. However, due to the model complexity, WaveNet always requires a large amount of training data, which has limited its applications in voice conversion, where training d
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Scalpnet: Detection Of Spatiotemporal Abnormal Intervals In Epileptic Eeg Using Convolutional Neural Networks
We propose ScalpNet: A deep neural network to detect spatiotemporal abnormal intervals from EEGs of epilepsy patients. Since the number of trained clinicians is very limited, it is very crucial to establish automatic detection of abnormal signals caused b
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Video Frame Interpolation Via Exceptional Motion-Aware Synthesis
In this paper, we propose a novel video frame interpolation method via exceptional motion-aware synthesis, in which accurate optical flow could be estimated even with exceptional motion patterns. Specifically, we devise two deep learning modules: exceptio
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Fixed-Point Optimization Of Transformer Neural Network
The Transformer model adopts a self-attention structure and shows very good performance in various natural language processing tasks. However, it is difficult to implement the Transformer in embedded systems because of its very large model size. In this s
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Bangla Voice Command Recognition In End-To-End System Using Topic Modeling Based Contextual Rescoring
In this work, we perform contextual rescoring using multi-label topic modeling to improve the performance of an End-to-End Bangla voice command recognition system. We use a hybrid of Connectionist Temporal Classification (CTC) and Attention mechanism in o
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Study Of Closed Phase Resonance Bandwidths For Oral And Nasal Tracts Using Zero Time Windowing
The periodic opening and closing of the vibrating vocal folds changes the production system continuously during the pro- duction of voiced speech. The subglottal and supraglottal cavities have distinct structure and impedance. A coupling and decoupling of
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A Robust Speaker Clustering Method Based On Discrete Tied Variational Autoencoder
Recently, the speaker clustering model based on aggregation hierarchy cluster (AHC) is a common method to solve two main problems: no preset category number clustering and fix category number clustering. In general, model takes features like i-vectors as
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Re-Translation Strategies For Long Form, Simultaneous, Spoken Language Translation
We investigate the problem of simultaneous machine translation of long-form speech content. We target a continuous speech-to-text scenario, generating translated captions for a live audio feed, such as a lecture or play-by-play commentary. As this scenari
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Investigating Generalization In Neural Networks Under Optimally Evolved Training Perturbations
In this paper, we study the generalization properties of neural networks under input perturbations and show that minimal training data corruption by a few pixel modifications can cause drastic overfitting. We propose an evolutionary algorithm to search fo
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Sequence-To-Sequence Singing Synthesis Using The Feed-Forward Transformer
We propose a sequence-to-sequence singing synthesizer, which avoids the need for training data with pre-aligned phonetic and acoustic features. Rather than the more common approach of a content-based attention mechanism combined with an autoregressive dec
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Asr Error Correction And Domain Adaptation Using Machine Translation
Off-the-shelf pre-trained Automatic Speech Recognition (ASR) systems are an increasingly viable service for companies of any size building speech-based products. While these ASR systems are trained on large amounts of data, domain mismatch is still an iss
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Anisotropic Guided Filtering
The guided filter and its derivatives have been widely employed in many image processing and computer vision applications due to their low complexity and good edge-preservation properties. Despite this success, these variants are unable to handle more agg
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Fast High-Dimensional Kernel Filtering
The bilateral and nonlocal means filters are instances of kernel-based filters that are popularly used in image processing. It was recently shown that fast and accurate bilateral filtering of grayscale images can be performed using a low-rank approximatio
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Enriched Speech For Effortless Listening
Human-machine speech interaction is increasingly common in the industrialised world. A (natural or synthetic) speech output that is optimised for high intelligibility and low cognitive load is of interest for both academia and industry: ENRICH (www.enrich
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Video-Driven Speech Reconstruction
This demo will showcase our video-to-audio model which attempts to reconstruct speech from short videos of spoken statements. Our model does so in a completely end-to-end manner where raw audio is generated based on the input video. This approach bypasses
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
An Empirical Study On Acoustic Feedback Path Across Hearing Aid Users
Acoustic feedback is one of the major problems in hearing aid applications. During a fitting session of a modern hearing aid, typically a feedback path prediction or an in situ measurement of feedback path is used as part of the gain and earpiece prescrip
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Fast Block-Sparse Estimation For Vector Networks
While there is now a significant literature on sparse inverse covariance estimation, all that literature, with only a couple of exceptions, has dealt only with univariate (or scalar) networks where each node carries a univariate signal. However in many, p
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
On Modeling Asr Word Confidence
We present a new method for computing ASR word confidences that effectively mitigates the effect of ASR errors for diverse downstream applications, improves the word error rate of the 1-best result, and allows better comparison of scores across different
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Improving Reverberant Speech Training Using Diffuse Acoustic Simulation
We present an efficient and realistic geometric acoustic simulation approach for generating and augmenting training data in speech-related machine learning tasks. Our physically-based acoustic simulation method is capable of modeling occlusion, specular a
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Single-Shot Real-Time Multiple-Path Time-Of-Flight Depth Imaging For Multi-Aperture And Macro-Pixel Sensors
Multiple-Path Interference (MPI) is a major drawback of Time-of-Flight (ToF) sensors. MPI occurs when a ToF pixel receives more than a single light bounce from the scene. Current methods resolving more than a single return per pixel rely on the sequential
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Design-Gan: Cross-Category Fashion Translation Driven By Landmark Attention
The rise of generative adversarial networks has boosted a vast interest in the field of fashion image-to-image translation. However, previous methods do not perform well in cross-category translation tasks, e.g., translating jeans to skirts in fashion ima
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Near-Optimal Interference Exploitation 1-Bit Massive Mimo Precoding Via Partial Branch-And-Bound
In this paper, we focus on 1-bit precoding for large-scale antenna systems in the downlink based on the concept of constructive interference (CI). By formulating the optimization problem that aims to maximize the CI effect subject to the 1-bit constraint
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Theoretical Analysis Of Multi-Carrier Agile Phased Array Radar
Modern radar systems are expected to operate reliably in congested environments under cost and power constraints. A recent technology for realizing such systems is frequency agile radar (FAR), which transmits narrowband pulses in a frequency hopping manne
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A Bin Encoding Training Of A Spiking Neural Network Based Voice Activity Detection
Advances of deep learning for Artificial Neural Networks(ANNs) have led to significant improvements in the performance of digital signal processing systems implemented on digital chips. Although recent progress in low-power chips is remarkable, neuromorph
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Adaptive Knowledge Distillation Based On Entropy
Knowledge distillation (KD) approach is widely used in the deep learning field mainly for model size reduction. KD utilizes soft labels of teacher model, which contain the dark- knowledge that one-hot ground-truth does not have. This knowledge can improve
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Audio-Based Auto-Tagging With Contextual Tags For Music
Music listening context such as location or activity has been shown to greatly influence the users' musical tastes. In this work, we study the relationship between user context and audio content in order to enable context-aware music recommendation agnost
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Discrete Wasserstein Autoencoders For Document Retrieval
Learning to hash via generative models has become a promising paradigm for fast similarity search in document retrieval. The binary hash codes are treated as Bernoulli latent variables when training a variational autoencoder (VAE). However, the prior of d
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
On Harmonic Approximations Of Inharmonic Signals
In this work, we present the misspecified Gaussian Cram'er-Rao lower bound for the parameters of a harmonic signal, or pitch, when signal measurements are collected from an almost, but not quite, harmonic model. For the asymptotic case of large sample si
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Denoising Of Event-Based Sensors With Spatial-Temporal Correlation
As a novel asynchronous-driven cameras, event-based sensors are with high sensitivity, fast speed and low data volume, but with abundant noise. Since the output of event-based sensors is in the form of address-event-representation (AER), the traditional f
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Dense Residual Network For Retinal Vessel Segmentation
Retinal vessel segmentation plays an imaportant role in the field of retinal image analysis because changes in retinal vascular structure can aid in the diagnosis of diseases such as hypertension and diabetes. In recent research, numerous successful segme