Showing 251 - 300 of 1951
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Aipnet: Generative Adversarial Pre-Training Of Accent-Invariant Networks For End-To-End Speech Recognition
As one of the major sources in speech variability, accents have posed a grand challenge to the robustness of speech recognition systems. In this paper, our goal is to build a unified end-to-end speech recognition system that generalizes well across accent
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Mobility-Aware Beam Steering In Metasurface-Based Programmable Wireless Environments
Programmable wireless environments (PWEs) utilize electromagnetic metasurfaces to transform wireless propagation into a software-controlled resource. In this work we study the effects of user device mobility on the efficiency of PWEs. An analytical model
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Knowledge Enhanced Latent Relevance Mining For Question Answering
Answer selection which aims to select the most appropriate answer from a pre-selected candidate pool has become increasingly important in a variety of practical applications. Previous work tends to use complex attention mechanisms to capture contextual re
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
On Network Science And Mutual Information For Explaining Deep Neural Networks
In this paper, we present a new approach to interpreting deep learning models. By coupling mutual information with network science, we explore how information flows through feedforward networks. We show that efficiently approximating mutual information al
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A Memory Augmented Architecture For Continuous Speaker Identification In Meetings
We introduce and analyze a novel approach to the problem of speaker identification in multi-party recorded meetings. Given a speech segment and a set of available candidate profiles, a data-driven approach is proposed learning the distance relations betwe
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
New Metrics For Evaluating The Accuracy Of Fundamental Frequency Estimation Approaches In Musical Signals
This paper demonstrates the importance of assessing the performance of fundamental frequency estimation algorithms on note-level descriptors in addition to frame-level accuracy. Note-level descriptors provide a better description of the human experience o
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Adversarial Mixup Synthesis Training For Unsupervised Domain Adaptation
Domain adversarial training is a popular approach for Unsupervised Domain Adaptation~(DA). However, the transferability of adversarial training framework may drop greatly on the adaptation tasks with a large distribution divergence between source and targ
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Compare Learning: Bi-Attention Network For Few-Shot Learning
Learning with few labeled data is a key challenge for visual recognition, as deep neural networks tend to overfit using a few samples only. One of the Few-shot learning methods called metric learning addresses this challenge by first learning a deep dista
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Robust Frequency-Domain Recursive Least M-Estimate Adaptive Filter For Acoustic System Identification
To identify acoustic systems in non-Gaussian and Gaussian noises, a robust frequency-domain recursive least M-estimate (FRLM) adaptive filtering algorithm is proposed. The cost function of the adaptive filter is defined by using a robust time-domain M-est
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Vggsound: A Large-Scale Audio-Visual Dataset
Our goal is to collect a large-scale audio-visual dataset with low label noise from videos `in the wild' using computer vision techniques. The resulting dataset can be used for training and evaluating audio recognition models. We make three contributions.
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A Simple And Efficient Iterative Method For Toa Localization
This paper develops a simple and efficient method for source localization using signal time-of-arrival (TOA) measurements. There exist many TOA localization algorithms, most of which require matrix inversions. Their complexity often makes them unsuitable
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Automatic And Simultaneous Adjustment Of Learning Rate And Momentum For Stochastic Gradient-Based Optimization Methods
Stochastic gradient-based methods are prominent for training machine learning and deep learning models. The performance of these techniques depends on their hyperparameter tuning over time and varies for different models and problems. Manual adjustment of
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Guided Learning For Weakly-Labeled Semi-Supervised Sound Event Detection
We propose a simple but efficient method termed Guided Learning for weakly-labeled semi-supervised sound event detection (SED). There are two sub-targets implied in weakly-labeled SED: audio tagging and boundary detection. Instead of designing a single mo
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Transmit Beampattern Shaping Via Waveform Design In Cognitive Mimo Radar
This paper is focused on designing a set of constant modulus waveform for cognitive Multiple-Input Multiple-Output (MIMO) radar systems. The aim is to shape the beampattern in transmitter to minimize the Integrated Side-lobe Level (ISL) in spatial domain
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Power Optimization Using Embedded Automatic Gain Control Algorithm With Photoplethysmography Signal Quality Classification
This paper presents the design and implementation of an Automatic Gain Control (AGC) embedded algorithm for photoplethysmographic (PPG) sensors. We use a number of statistical and spectral characteristics of the raw and filtered PPG signals, referred to a
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Fir Filter Design And Implementation For Phase-Based Processing
Complex steerable pyramid (CSP) is widely used to decompose images into muti-scale and oriented subbands for phase-based processing, such as video magnification, frame interpolation, and view synthesis. The conventional implementation is based on frequenc
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Low-Tubal-Rank Tensor Recovery From One-Bit Measurements
This paper focuses on the recovery of low-tubal-rank tensors from binary measurements under the frame of tensor Singular Value Decomposition. We show that the direction of a tubal-rank-$r$ tensor $m{mathcal{X}}in R^{n_1 imes n_2 imes n_3}$ can be a
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Cooperative Learning Via Federated Distillation Over Fading Channels
Cooperative training methods for distributed machine learning are typically based on the exchange of local gradients or local model parameters. The latter approach is known as Federated Learning (FL). An alternative solution with reduced communication ove
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Complex Transformer: A Framework For Modeling Complex-Valued Sequence
While deep learning has received a surge of interest in a variety of fields in recent years, major deep learning models barely use complex numbers. However, speech, signal and audio data are naturally complex-valued after Fourier Transform, and studies ha
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Robust Matrix Completion Via Lp-Greedy Pursuits
A novel $ell_p$-greedy pursuit (GP) algorithm for robust matrix completion, i.e., recovering a low-rank matrix from only a subset of its noisy and outlier-contaminated entries, is devised. The $ell_p$-GP uses the strategy of sequential rank-one update.
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Robust Tdoa Indoor Tracking Using Constrained Measurement Filtering And Grid-Based Filtering
This paper considers exploiting the time difference of arrival (TDOA) measurements from a ultra wideband (UWB) indoor positioning system to locate a moving point target. In indoor environments, measured TDOAs are subject to large errors due to multipath a
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Sequence-Level Consistency Training For Semi-Supervised End-To-End Automatic Speech Recognition
This paper presents a novel semi-supervised end-to-end automatic speech recognition (ASR) method that employs consistency training with the use of unlabeled data. In consistency training, unlabeled data can be utilized for constraining a model such that i
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Cross-Speaker Silent-Speech Command Word Recognition Using Electro-Optical Stomatography
Speech recognition based on articulatory movements instead of the acoustic signal is of growing interest in the community. In this work, we present the results of a study using a novel measurement technology called Electro-Optical Stomatography to capture
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Learning Semi-Supervised Anonymized Representations By Mutual Information
This paper addresses the problem of removing from a set of data (here images) a given private information, while still allowing other utilities on the processed data. This is obtained by training concurrently a GAN-like discriminator and an autoencoder. T
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Decoding 5G-Nr Communications Via Deep Learning
Upcoming modern communications are based on 5G specifications and aim at providing solutions for novel vertical industries. One of the major changes of the physical layer is the use of Low-Density Parity-Check (LDPC) code for channel coding. Although LDPC
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Teaching Signals And Systems - A First Course In Signal Processing
Signals and systems is a well known fundamental course in signal processing. How this course is taught to a student can spell the difference between whether s/he pursues a career in this field or not. Giving due consideration to this matter, this paper re
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Looking Enhances Listening: Recovering Missing Speech Using Images
Speech is understood better by using visual context; for this reason, there have been many attempts to use images to adapt automatic speech recognition (ASR) systems. Current work, however, has shown that visually adapted ASR models only use images as a r
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A Hierarchical Model For Dialog Act Recognition Considering Acoustic And Lexical Context Information
Dialog act recognition (DAR) is important to capture speakers' intention in a dialog system. Traditional methods commonly use the lexical information from transcripts, acoustic information from speech, and dialog context information to do DAR. However, in
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A Low-Complexity Map Detector For Distributed Networks
This work describes a generalization of our previous maximum likelihood (ML) detector to a maximum a posteriori (MAP) detector in distributed networks using the diffusion LMS algorithm. Nodes in the network must decide between two concurrent hypotheses co
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Non-Parametric Community Change-Points Detection In Streaming Graph Signals
Detecting changes in network-structured time series data is of utmost importance in critical applications as diverse as detecting denial of service attacks against online service providers or monitoring energy and water supplies. The aim of this paper is
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Detect Insider Attacks Using Cnn In Decentralized Optimization
This paper studies the security issue of a gossip-based distributed projected gradient (DPG) algorithm, when it is applied for solving a decentralized multi-agent optimization. It is known that the gossip-based DPG algorithm is vulnerable to insider attac
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
What Is Best For Spoken Language Understanding: Small But Task-Dependant Embeddings Or Huge But Out-Of-Domain Embeddings?
Word embeddings are shown to be a great asset for several Natural Language and Speech Processing tasks. While they are already evaluated on various NLP tasks, their evaluation on spoken or natural language understanding (SLU) is less studied. The goal of
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Robust Hybrid Precoding For Interference Exploitation In Massive Mimo Systems
In this paper, we consider a multiuser massive MIMO system with hybrid analog-digital precoding architecture. The phase shifters in the hybrid precoding architecture are assumed to be imperfect, where the true values of both phase and magnitude of the pha
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Estimating Centrality Blindly From Low-Pass Filtered Graph Signals
This paper considers blind methods for centrality estimation from graph signals. We model graph signals as the outcome of an unknown low-pass graph filter excited with influences governed by a sparse sub-graph. This model is compatible with a number of da
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Opportunistic Use Of Gnss Signals To Characterize The Environment By Means Of Machine Learning Based Processing
GNSS is widely used to provide positions in an absolute reference frame in Unmanned Aerial Vehicles (UAV) and Unmanned Ground Vehicles (UGV), where GNSS is merged with the information provided by other sensors. Even if the main goal of GNSS signal process
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Human-Machine Collaboration For Medical Image Segmentation
Image segmentation is a ubiquitous step in almost any medical image study. Deep learning-based approaches achieve state-of-the-art in the majority of image segmentation benchmarks. However, end-to-end training of such models requires sufficient annotation
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Data-Driven Wind Speed Estimation Using Multiple Microphones
A deep neural network (DNN) based approach for estimating the speed of airflows using closely-spaced microphones is proposed. The spatial characteristics of wind noise measured with a small-aperture array are exploited, i.e., the low-frequency spatial coh
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Unsupervised Pretraining Transfers Well Across Languages
Cross-lingual and multi-lingual training of Automatic Speech Recognition (ASR) has been extensively investigated in the supervised setting. This assumes the existence of a parallel corpus of speech and orthographic transcriptions. Recently, contrastive pr
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Object Surface Estimation From Radar Images
In this paper we develop a deep neural network (DNN) method for estimating the object surface from radar 2D image (azimuth-range). The DNN is designed to maintain the input image angular resolution and produces two outputs per each angle, which are a clas
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Inverse Multiple Scattering With Phaseless Measurements
We study the problem of reconstructing an object from phaseless measurements in the context of inverse multiple scattering. Our formulation explicitly decouples the variables that represent the unknown object image and the unknown phase, respectively, in
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Accuracy-Robustness Trade-Off For Positively Weighted Neural Networks
This work proposes a new learning strategy for training a feedforward neural network subject to spectral norm and nonnegativity constraints. Our primary goal is to control the Lipschitz constant of the network in order to make it robust against adversaria
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis
Despite the ability to produce human-level speech for in-domain text, attention-based end-to-end text-to-speech (TTS) systems suffer from text alignment failures that increase in frequency for out-of-domain text. We show that these failures can be address
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Building Firmly Nonexpansive Convolutional Neural Networks
Building nonexpansive Convolutional Neural Networks (CNNs) is a challenging problem that has recently gained a lot of attention from the image processing community. In particular, it appears to be the key to obtain convergent Plug-and-Play algorithms. Thi
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Autoregressive Parameter Estimation With Dnn-Based Pre-Processing
In this paper, a method for estimating the autoregressive parameters from a signal segment is proposed. The method is based on a deep neural network (DNN) in combination with the classical Levinson-Durbin recursion (LDR). The DNN acts as a pre-processor f
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Variable Projection For Multiple Frequency Estimation
The estimation of the frequencies of multiple complex sinusoids in the presence of noise is required in many applications such as sonar, speech processing, communications, and power systems. According to previous works [1,2], this problem can be reformula
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Mixup Multi-Attention Multi-Tasking Model For Early-Stage Leukemia Identification
Recently, several image processing and deep learning techniques have been applied to automate the detection of Acute Lymphoblastic Leukemia cells (ALL). However, most of them have consistently focused on classification mature stage cell images into binary
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Effectiveness Of Self-Supervised Pre-Training For Asr
We compare self-supervised representation learning algorithms which either explicitly quantize the audio data or learn representations without quantization. We find the former to be more accurate since it builds a good vocabulary of the data through vq-wa
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Lstm-Based One-Pass Decoder For Low-Latency Streaming
Current state-of-the-art models based on Long-Short Term Memory (LSTM) networks have been extensively used in automatic speech recognition (ASR) to improve the performance of these systems. However, using them under a streaming setup is not straightforwar