Cart
Create Account
Sign In
Showing 351 - 400 of 1951
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Crowdsourcing-Based Ranking Aggregation For Person Re-Identification
Person re-identification (re-ID) is widely applied in surveillance and criminal detection applications. The existing research focus on devising the stand-alone re-ID methods, ignoring their practical application in the multi-person collaboration scenario.
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Voice Conversion With Transformer Network
This paper describes an end-to-end voice conversion system, which involves three main ideas: transformer, context preservation mechanisms, and model adaptation. Self-attention in the transformer architecture directly connects all positions, making it easi
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Masking And Inpainting: A Two-Stage Speech Enhancement Approach For Low Snr And Non-Stationary Noise
Currently, low signal-to-noise ratio (SNR) and non-stationary noise cause severe performance degradation for most of speech enhancement models. For better speech enhancement at the above scenarios, this paper proposes a two-stage approach that consists of
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
How Much Self-Attention Do We Need? Trading Attention For Feed-Forward Layers
We propose simple architectural modifications in the standard Transformer with the goal to reduce its total state size (defined as the number of self-attention layers times the sum of the key and value dimensions, times position) without loss of performan
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Empirical Sure-Guided Microscopy Super-Resolution Image Reconstruction From Confocal Multi-Array Detectors
The new generation of confocal microscopes are equipped with an array detector that generates an array of images corresponding to a multiview of the same sample. Several computational methods have been proposed to reconstruct a single super-resolution ima
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Artificial Bandwidth Extension Using Conditional Variational Auto-Encoders And Adversarial Learning
Artificial bandwidth extension (ABE) algorithms have been developed to estimate missing highband frequency components (4-8kHz) to improve quality of narrowband (0-4kHz) telephone calls. Most ABE solutions employ deep neural networks (DNNs) due to their we
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Global Structure Graph Guided Fine-Grained Vehicle Recognition
Fine-grained vehicle recognition is a challenging problem due to the subtle intra-category appearance variation, which requires the recognition model can capture discriminative features from distinguishing regions. The structure is an important characteri
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A Robust Audio-Visual Speech Enhancement Model
Most existing audio-visual speech enhancement (AVSE) methods work well in conditions with strong noise,however when applied to conditions with a medium SNR, serious performance degradations are often observed. These degradations can be partly attributed t
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Challenges And Perspectives In Neuromorphic-Based Visual Iot Systems And Networks
Neuromorphic sensors, a.k.a. dynamic vision sensors (DVS) or silicon retinas, do not capture full images (frames) at a fixed rate, but asynchronously capture spikes indicating changes of brightness in the scene, following the principles of biological visi
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
$\Beta$-Nmf And Sparsity Promoting Regularizations For Complex Mixture Unmixing. Application To 2D Hsqc Nmr.
In Nuclear Magnetic Resonance (NMR) spectroscopy, an efficient analysis and a relevant extraction of different molecule properties from a given chemical mixture are important tasks, especially when processing bidimensional NMR data. To that end, using a b
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Channel Invariant Speaker Embedding Learning With Joint Multi-Task And Adversarial Training
Using deep neural network to extract speaker embedding has significantly improved the speaker verification task. However, such embeddings are still vulnerable to channel variability. Previous works have used adversarial training to suppress channel inform
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Effect Of Undersampling On Non-Negative Blind Deconvolution With Autoregressive Filters
This paper considers the problem of blind deconvolution where the input signal is non-negative and sparse, and the unknown convolutional kernel is a first order autoregressive filter. Our objective is to understand if it is possible to recover both the si
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Image Fusion Using Joint Sparse Representations And Coupled Dictionary Learning
The image fusion problem consists in combining complementary parts of multiple images captured, for example, with different focal settings into one image of higher quality. This requires the identification of the sharpest areas in sets of input images. Re
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Effects Of Spectral Tilt On Listeners' Preferences And Intelligibility
High intelligibility can be achieved when listening to synthetic or artificially-produced speech under adverse conditions. But can listener preferences reveal any extra information when intelligibility is at ceiling? This paper describes a real-time speec
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
The Picasso Algorithm For Bayesian Localization Via Paired Comparisons In A Union Of Subspaces Model
We develop a framework for localizing an unknown point $\w$ using paired comparisons of the form ``$\w$ is closer to point $\x_i$ than to $\x_j$'' when the points lie in a union of known subspaces. This model, which extends a broad class of existing metho
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Polyphonic Sound Event Detection Using Transposed Convolutional Recurrent Neural Network
In this paper we propose a Transposed Convolutional Recurrent Neural Network (TCRNN) architecture for polyphonic sound event recognition. Transposed convolution layer, which caries out a regular convolution operation but reverts the spatial transformation
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Precise Performance Analysis Of The Box-Elastic Net Under Matrix Uncertainties
In this letter, we consider the problem of recovering an unknown sparse signal from noisy linear measurements, using an enhanced version of the popular Elastic-Net (EN) method.We modify the EN by adding a box-constraint, and we call it the Box-Elastic Net
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Real-Time Epileptic Seizure Detection During Sleep Using Passive Infrared (Pir) Sensors
According to World Health Organization (WHO), millions of people suffer from epilepsy, which is a chronic disorder of the brain. Sudden Unexplained Death in Epilepsy (SUDEP) is considered as one of the most dangerous threats to the patients who suffer fro
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Self-Tuning Algorithms For Multisensor-Multitarget Tracking Using Belief Propagation
Situation-aware technologies enabled by multitarget tracking algorithms will create new services and applications in emerging fields such as autonomous navigation and maritime surveillance. The system models underlying multitarget tracking algorithms ofte
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A Single-Wavelength Real-Time Material-Sensing Camera Based On Time-Of-Flight Measurements
Time-of-Flight (ToF) cameras provide a fast and robust way of acquiring the 3D shape of real scenes. Dense depth images can be generated at tens of frame per second. 3D shapes can be then segmented and objects classified, but can we directly sense the obj
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Effective Pipeline For Compressing Deep Object Detectors
To alleviate the deployment of deep object detectors with large model capacity and complex computation, an effective model compression pipeline is designed in this paper. Firstly, attributed to the refined soft filter pruning, 3D filters of each convoluti
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A Noninvasive Method To Detect Diabetes Mellitus And Lung Cancer Using The Stacked Sparse Autoencoder
Diabetes mellitus and lung cancer are two of the most common fatal diseases in the world, causing considerable deaths every year. However, it is not easy to detect diabetes mellitus and lung cancer efficiently--needing professional medical instruments suc
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
On The Use Of RéNyi Entropy For Optimal Window Size Computation In The Short-Time Fourier Transform
This paper investigates the determination of an optimal window length associated with the computation of the short time Fourier transform of multicomponent signals. For that purpose, the minimum of the Rényi entropy has been widely used in recent years. H
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Steganography And Its Detection In Jpeg Images Obtained With The "trunc"
Many portable imaging devices use the operation of "trunc" (rounding towards zero) instead of rounding as the final quantizer for computing DCT coefficients during JPEG compression. We show that this has rather profound consequences for steganography and
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Reflectance-Guided, Contrast-Accumulated Histogram Equalization
Existing image enhancement methods fall short of expectations because with them it is difficult to improve global and local image contrast simultaneously. To address this problem, we propose a histogram equalization-based method that adapts to the data-de
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Joint Training Of Deep Neural Networks For Multi-Channel Dereverberation And Speech Source Separation
In this paper, we propose a joint training of two deep neural networks (DNNs) for dereverberation and speech source separation. The proposed method connects the first DNN, the dereverberation part, the second DNN, and the speech source separation part in
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Hidden Markov Models For Sepsis Detection In Preterm Infants
We explore the use of traditional and contemporary hidden Markov models (HMMs) for sequential physiological data analysis and sepsis prediction in preterm infants. We investigate the use of classical Gaussian mixture model based HMM, and a recently propos
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A Hybrid Structural Sparse Error Model For Image Deblocking
Inspired by the image nonlocal self-similarity (NSS) prior, structural sparse representation (SSR) models exploit each group as the basic unit for sparse representation, which have achieved promising results in various image restoration applications. Howe
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Manet: Multi-Scale Aggregated Network For Light Field Depth Estimation
We present a novel end-to-end network, MANet, for light field depth estimation. MANet is a parameter-effective and efficient multi-scale aggregated network, which is about 3 times smaller and 3 times faster than the current top-performing method Epinet. T
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Deep Learning For Robust Power Control For Wireless Networks
Robust optimization is an important task in wireless communications, because due to fading and feedback delay there is inherent uncertainty in channel state information in a wireless environment. This paper aims to show that a deep learning approach for n
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Continual Learning Through One-Class Classification Using Vae
Artificial neural networks (ANNs) suffer from catastrophic forgetting, a sharp decrease in performance on previously learned tasks, when trained on a new task without constant rehearsal. In this paper, we propose a new method for overcoming this phenomeno
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Coincidence, Categorization, And Consolidation: Learning To Recognize Sounds With Minimal Supervision
Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on multimodal unsuperv
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Assimilation-Based Learning Of Chaotic Dynamical Systems From Noisy And Partial Data
Despite some promising results under ideal conditions (i.e. noise-free and complete observation), learning chaotic dynamical systems from real life data is still a very challenging task. We propose a novel framework, which combines data assimilation schem
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
We propose and evaluate transformer-based acoustic models for hybrid speech recognition. Several modeling choices are discussed in this work, including various positional embedding methods and an iterated loss to enable training deep transformers. We also
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Speaker Embeddings Incorporating Acoustic Conditions For Diarization
We present our work on training speaker embeddings, especially effective for speaker diarization. For various speaker recognition tasks, extracting speaker embeddings using Deep Neural Networks (DNNs) has become major methods. These embeddings are general
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Learning Perception And Planning With Deep Active Inference
Active inference is a process theory of the brain that states that all living organisms infer actions in order to minimize their (expected) free energy. However, current experiments are limited to predefined, often discrete, state spaces. In this paper we
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Hearing Aid Research Data Set For Acoustic Environment Recognition
State-of-the-art hearing aids (HA) are limited in recognizing acoustic environments. Much effort is spent on research to improve listening experience for HA users in every acoustic situation. There is, however, no dedicated public database to train acoust
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Recurrent Neural Audiovisual Word Embeddings For Synchronized Speech And Real-Time Mri
In this paper, the use of word embeddings for the segments found in audio and real-time magnetic resonance imaging (rtMRI) videos is addressed. In this study, word embeddings are created to store and retrieve data efficiently, and their representation pow
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
1.5Gbit/S 4.9W Hyperspectral Image Encoders On A Low-Power Parallel Heterogeneous Processing Platform
This work explores the utilization of low-power heterogeneous devices for parallelizing the compute-intensive hyper-spectral and multispectral image compression CCSDS-123 entropy encoders. Multithread processing allows for the near-optimal system?s bandwi
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Improving Music Transcription By Pre-Stacking A U-Net
We propose to pre-stack a U-Net as a way of improving the polyphonic music transcription performance of various baseline Convolutional Neural Networks (CNNS). The U-Net, a network architecture based on skip-connections between layers acts as a transformat
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Privacy Aware Acoustic Scene Synthesis Using Deep Spectral Feature Inversion
Gathering information about the acoustic environment of urban areas is now possible and studied in many major cities in the world. Part of the research is to find ways to inform the citizen about its sound environment while ensuring her privacy. We study