Showing 1651 - 1700 of 1951
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A Model-Free Approach To Distributed Transmit Beamforming
This paper presents a model-free solution to distributed transmit beamforming using mobile agents. Each agent is equipped with an antenna and the agents represent the individual elements in an antenna array. The agents are tasked to coordinate their relat
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Gaussian Lpcnet For Multisample Speech Synthesis
LPCNet vocoder has recently been presented to TTS community and is now gaining increasing popularity due to its effectiveness and high quality of the speech synthesized with it. In this work, we present a modification of LPCNet that is 1.5x faster, has tw
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Source Domain Data Selection For Improved Transfer Learning Targeting Dysarthric Speech Recognition
This paper presents an improved transfer learning framework applied to robust personalised speech recognition models for speakers with dysarthria. As the baseline of transfer learning, a state-of-the-art CNN-TDNN-F ASR acoustic model trained solely on sou
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Semi-Implicit Stochastic Recurrent Neural Networks
Stochastic recurrent neural networks with latent random variables of complex dependency structures have shown to be more successful in modeling sequential data than deterministic deep models. However, the majority of existing methods have limited expressi
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Decentralized Stochastic Non-Convex Optimization Over Weakly Connected Time-Varying Digraphs
In this paper, we consider decentralized stochastic non-convex optimization over a class of weakly connected digraphs. First, we quantify the convergence behaviors of the weight matrices of this type of digraphs. By leveraging the perturbed push sum proto
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Time-Frequency Loss For Cnn Based Speech Super-Resolution
Speech super-resolution (SR), also called speech bandwidth extension (BWE), aims to increase the sampling rate of a given lower resolution speech signal. Recent years have witnessed the successful application of deep neural networks in time or frequency d
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Dynamic Resource Allocation For Wireless Edge Machine Learning With Latency And Accuracy Guarantees
In this paper, we address the problem of dynamic allocation of communication and computation resources for Edge Machine Learning (EML) exploiting Multi-Access Edge Computing (MEC). In particular, we consider an IoT scenario, where sensor devices collect d
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Sampling Classes Of Non-Bandlimited Signals Using Integrate-And-Fire Devices: Average Case Analysis
We investigate the use of integrate-and-fire systems to efficiently sample classes of non-bandlimited signals such as bursts of spikes. The sampling in this case is based on storing some timing information about the signal, and no information about its am
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Improving Robustness Of Deep Learning Based Monaural Speech Enhancement Against Processing Artifacts
In voice telecommunication, the intelligibility and quality of speech signals can be severely degraded by background noise if the speaker at the transmitting end talks in a noisy environment. Therefore, a speech enhancement system is typically integrated
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Lookahead Converges To Stationary Points Of Smooth Non-Convex Functions
The Lookahead optimizer [Zhang et al., 2019] was recently proposed and demonstrated to improve performance of stochastic first-order methods for training deep neural networks. Lookahead can be viewed as a two time-scale algorithm, where the fast dynamics
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Constant-Envelope Precoding For Satellite Systems
In this paper, Constant-Envelope Precoding techniques are presented for satellite-based communication systems. In the developed transmission technique the signals of the antennas are designed to be of constant amplitude, improving the robustness of the la
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Cost Aware Adversarial Learning
The problem of making the classifier design resilient to test data falsification is considered. In the literature, a few countermeasures have been proposed to defend machine learning algorithms against test data falsification, but a common assumption empl
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Universal Phone Recognition With A Multilingual Allophone System
Recently, multilingual speech recognition has achieved tremendous progress by sharing parameters across languages. Multilingual acoustic models, however, generally ignore the difference between phonemes (sounds that can support lexical contrasts in a emp
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Learning Partial Differential Equations From Data Using Neural Networks
We develop a framework for estimating unknown partial differential equations (PDEs) from noisy data, using a deep learning approach. Given noisy samples of a solution to an unknown PDE, our method interpolates the samples using a neural network, and extra
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Local-Global Feature For Video-Based One-Shot Person Re-Identification
One-shot video-based re-identification, which uses only one labeled tracklet for each identity, is challenging since the framework usually suffers misalignment and inefficient utilizing of unlabeled data. In this paper we propose a novel local-global prog
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Toward Better Speaker Embeddings: Automated Collection Of Speech Samples From Unknown Distinct Speakers
The accuracy of speaker verification and diarization models depends on the quality of the speaker embeddings used to separate audio samples from different speakers. With the goal of training better embedding models, we devise an au- tomatic pipeline for l
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Fully-Hierarchical Fine-Grained Prosody Modeling For Interpretable Speech Synthesis
This paper proposes a hierarchical, fine-grained and interpretable latent variable model for prosody based on the Tacotron 2 text-to-speech model. It achieves multi-resolution modeling of prosody by conditioning finer level representations on coarser leve
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Real-Time, Universal, And Robust Adversarial Attacks Against Speaker Recognition Systems
As the popularity of voice user interface (VUI) exploded in recent years, speaker recognition system has emerged as an important medium of identifying a speaker in many security-required applications and services. In this paper, we propose the first real-
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A Simple But Effective Bert Model For Dialog State Tracking On Resource-Limited Systems
In a task-oriented dialog system, the goal of dialog state tracking (DST) is to monitor the state of the conversation from the dialog history. Recently, many deep learning based methods have been proposed for the task. Despite their impressive performance
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Speaker-Aware Target Speaker Enhancement By Jointly Learning With Speaker Embedding Extraction
Deep learning based speech separation approaches have received great interest, among which the recent speaker-aware speech enhancement methods are promising for solving difficulties such as arbitrary source permutation and unknown number of sources. In th
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Wawenets: A No-Reference Convolutional Waveform-Based Approach To Estimating Narrowband And Wideband Speech Quality
Building on prior work we have developed a no-reference (NR) waveform-based convolutional neural network (CNN) architecture that can accurately estimate speech quality or intelligibility of narrowband and wideband speech segments. These Wideband Audio Wav
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Automatic Fluency Evaluation Of Spontaneous Speech Using Disfluency-Based Features
This paper describes an automatic fluency evaluation of spontaneous speech. Although we regularly observe a variety of different disfluencies in spontaneous speech, we focus on two types of phenomena, i.e., filled pauses and word fragments. This paper aim
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A Time-Frequency Network With Channel Attention And Non-Local Modules For Artificial Bandwidth Extension
Convolution neural networks (CNNs) have been achieving increasing attention for the artificial bandwidth extension (ABE) task recently. However, these methods use the flipped low-frequency phase to reconstruct speech signals, which may lead to the well-kn
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Interpretable Self-Attention Temporal Reasoning For Driving Behavior Understanding
Performing driving behaviors based on causal reasoning is essential to ensure driving safety. In this work, we investigated how state-of-the-art 3D Convolutional Neural Networks (CNNs) perform on classifying driving behaviors based on causal reasoning. We
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Polarizing Front Ends For Robust Cnns
The vulnerability of deep neural networks to small, adversarially designed perturbations can be attributed to their ?excessive linearity.? In this paper, we propose a bottom-up strategy for attenuating adversarial perturbations using a nonlinear front end
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A Novel Rank Selection Scheme In Tensor Ring Decomposition Based On Reinforcement Learning For Deep Neural Networks
Tensor decomposition has been proved to be effective for solving many problems in signal processing and machine learning. Recently, tensor decomposition finds its advantage for compressing deep neural networks. In many applications of deep neural networks
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Voice Based Classification Of Patients With Amyotrophic Lateral Sclerosis, Parkinson's Disease And Healthy Controls With Cnn-Lstm Using Transfer Learning
In this paper, we consider 2-class and 3-class classification problems for classifying patients with Amyotrophic Lateral Sclerosis (ALS), Parkinson?s Disease (PD), and Healthy Controls (HC) using a CNN-LSTM network. Classification performance is examined
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Automatic Event Detection Of Rem Sleep Without Atonia From Polysomnography Signals Using Deep Neural Networks
Rapid eye movement (REM) sleep behavior disorder (RBD) is a sleep disorder that features loss of atonia, or REM sleep without atonia (RSWA). RBD and RSWA are early manifestations of degenerative neurological diseases such as Parkinson's and Lewy Body Deme
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Mahalanobis Distance Based Adversarial Network For Anomaly Detection
Anomaly detection techniques are very crucial in multiple business applications, such as cyber security, manufacturing and finance. However, developing anomaly detection methods for high-dimensional data with high speed and good performance is still a cha
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Time-Domain Neural Network Approach For Speech Bandwidth Extension
In this paper, we study the time-domain neural network approach for speech bandwidth extension. We propose a network architecture, named multi-scale fusion neural network (MfNet), that gradually restores the low-frequency signal and predicts the high-freq
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Exploiting Two-Dimensional Symmetry And Unimodality For Model-Free Source Localization In Harsh Environment
Knowing the location of a transceiver may enable advanced radio resource management strategies in sensing and communication networks. However, there are many scenarios where users operate in a non-cooperative mode with no localization-dedicated signaling
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Multi-Head Attention For Speech Emotion Recognition With Auxiliary Learning Of Gender Recognition
The paper presents a Multi-Head Attention deep learning network for Speech Emotion Recognition (SER) using Log mel-Filter Bank Energies (LFBE) spectral features as the input. The multi-head attention along with the position embedding jointly attends to in
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Generalized Graph Spectral Sampling With Stochastic Priors
We consider generalized sampling for stochastic graph signals. The generalized graph sampling framework allows recovery of graph signals beyond the bandlimited setting by placing a correction filter between the sampling and reconstruction operators and as
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
View-Angle Invariant Object Monitoring Without Image Registration
Object monitoring can be performed by change detection algorithms. However, for the image pair with a large perspective difference, the change detection performance is usually impacted by inaccurate image registration. To address the above difficulties, a
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Spoken Language Acquisition Based On Reinforcement Learning And Word Unit Segmentation
The process of spoken language acquisition has been one of the topics which attract the greatest interesting from linguists for decades. By utilizing modern machine learning techniques, we simulated this process on computers, which helps to understand the
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Investigation Of Methods To Improve The Recognition Performance Of Tamil-English Code-Switched Data In Transformer Framework
Code-switching (CS) refers to (inter/intra-word) switching between multiple languages in a single conversation. In multilingual countries like India, CS occurs very often in everyday speech, resulting in a new breed of languages in urban regions like Hing
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Video Deblurring Via 3D Cnn And Fourier Accumulation Learning
Camera shake and target movement often leads to undesirable image blurring in videos. How to exploit spatial-temporal information of adjacent frames and reduce the processing time of deblurring are two major issues in video deblurring. In this paper, we p
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Hydranet: A Real-Time Waveform Separation Network
Real-time source separation has become increasingly important, as more and more applications, such as voice recognition and voice commands, require clean audio input in noisy environments. Recent developments in deep learning have allowed models to direct
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Computability Of The Peak Value Of Bandlimited Signals
In this paper we study the peak value problem, i.e., the task of computing the peak value of a bandlimited signal from its samples. The peak value problem is important, for example, in communications, where the peak value of the transmit signal has to be
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Meta-Learning Extractors For Music Source Separation
We propose a hierarchical meta-learning-inspired model for music source separation (Meta-TasNet) in which a generator model is used to predict the weights of individual extractor models. This enables efficient parameter-sharing, while still allowing for i
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Unsupervised Variational Bayesian Kalman Filtering For Large-Dimensional Gaussian Systems
This paper considers the unsupervised filtering problem for large-dimensional linear and Gaussian systems, a setup in which the optimal Kalman filter (KF) might not be usable due to the exorbitant computational cost and storage requirements. For this prob
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Cross-Stained Segmentation From Renal Biopsy Images Using Multi-Level Adversarial Learning
Segmentation from renal pathological images is a key step in automatic analyzing the renal histological characteristics. However, the performance of models varies significantly in different types of stained datasets due to the appearance variations. In th
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Multi-Conditioning And Data Augmentation Using Generative Noise Model For Speech Emotion Recognition In Noisy Conditions
Degradation due to additive noise is a significant road block in the real-life deployment of Speech Emotion Recognition (SER) systems. Most of the previous work in this field dealt with the noise degradation either at the signal or at the feature level. I
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
3D Unknown View Tomography Via Rotation Invariants
In this paper, we study the problem of reconstructing a 3D point source model from a set of 2D projections at unknown view angles. Our method obviates the need to recover the projection angles by extracting a set of rotation-invariant features from the no
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Hierarchical Sequence Representation With Graph Network
Video classification problem is a challenging task in computer vision. The performance of this task is highly relied on the scale of training data and the effectiveness of video embedding via a robust embedding network. Unsupervised solutions such as feat
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
High-Resolution Attention Network With Acoustic Segment Model For Acoustic Scene Classification
[2 Videos ]
The spectral information of acoustic scenes is diverse and complex, which poses challenges for acoustic scene tasks. To improve the classification performance, a variety of convolutional neural networks (CNNs) are proposed to extract richer semantic infor