Showing 1 - 50 of 1951
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Action-Manipulation Attacks On Stochastic Bandits
As stochastic multi-armed bandit model has many important applications, understanding the impact of adversarial attacks on this model is essential for the safe applications of this model. In this paper, we propose a new class of attack named action-manipu
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Improving Speaker-Attribute Estimation By Voting Based On Speaker Cluster Information
This paper proposes a general post-processing method for improving speaker-attribute estimation. Estimating speaker-specific attributes such as age and gender is an important task with a wide range of applications. While the recent proposed deep neural ne
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Generalized Kernel-Based Dynamic Mode Decomposition
Reduced modeling in high-dimensional reproducing kernel Hilbert spaces offers the opportunity to approximate efficiently non-linear dynamics. In this work, we devise an algorithm based on low rank constraint optimization and kernel-based computation that
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Optimized Single Carrier Transceiver For Future Sub-Terahertz Applications
The performance of sub-THz communications, contemplated for the next generation of wireless networks, are significantly degraded by oscillator phase noise. In this paper, we address the design of a single carrier transceiver resilient to phase noise. This
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Asymptotic Stochastic Analysis Of Partially Relaxed Dml
The Partial Relaxation (PR) approach has recently been proposed to solve the Direction of Arrival (DoA) estimation problem. In this paper, we investigate the outlier production mechanism of the Partially Relaxed Deterministic Maximum Likelihood (PR-DML) D
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Overcoming High Nanopore Basecaller Error Rates For Dna Storage Via Basecaller-Decoder Integration And Convolutional Codes
As magnetization and semiconductor based storage technologies approach their limits, bio-molecules, such as DNA, have been identified as promising media for future storage systems, due to their high storage density (petabytes/gram) and long-term durabilit
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Multilingual Grapheme-To-Phoneme Conversion With Byte Representation
Grapheme-to-phoneme (G2P) models convert a written word into its corresponding pronunciation and are essential components in automatic-speech-recognition and text-to-speech systems. Recently, the use of neural encoder-decoder architectures has substantial
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Multi-Way Multi-View Deep Autoencoder For Image Feature Learning With Multi-Level Graph Regularization
Multi-view feature learning has garnered much attention recently since many real world data are comprised of different representations or views. How to explore the consensus structure and eliminate the inconsistency noise in different views remains a chal
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Spatial Active Noise Control Based On Kernel Interpolation With Directional Weighting
A spatial active noise control (ANC) method taking prior information on the approximate direction of primary noise sources into consideration is proposed. ANC aims to cancel incoming primary noise using secondary loudspeakers. Conventional multipoint ANC
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Using Automatic Speech Recognition And Speech Synthesis To Improve The Intelligibility Of Cochlear Implant Users In Reverberant Listening Environments
Cochlear implant (CI) users experience substantial difficulties in understanding reverberant speech. A previous study proposed a strategy that leverages automatic speech recognition (ASR) to recognize reverberant speech and speech synthesis to translate t
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Speaker-Invariant Affective Representation Learning Via Adversarial Training
Representation learning for speech emotion recognition is challenging due to labeled data sparsity issue and lack of gold-standard references. In addition, there is much variability from input speech signals, human subjective perception of the signals and
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Deep Neural Network Based Matrix Completion For Internet Of Things Network Localization
In this paper, we propose a deep neural network based matrix completion approach for Internet of Things (IoT) localization. In the proposed method, we recast Euclidean distance matrix completion problem into the alternating minimization problem. By using
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Peer To Peer Offloading With Delayed Feedback: An Adversary Bandit Approach
Fog computing brings computation and services to the edge of networks enabling real time applications. In order to provide satisfactory quality of experience, the latency of fog networks needs to be minimized. In this paper, we consider a peer computation
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Structured Sparse Attention For End-To-End Automatic Speech Recognition
The Softmax normalization function-based attention mechanism is often employed by End-to-End Automatic Speech Recognition (E2E ASR) models to tell the network where to focus within the input. However, this mechanism leads to the attention distribution bec
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Deep-Neural-Network Based Fall-Back Mechanism In Interference-Aware Receiver Design
In this paper, we consider designing a fall-back mechanism in an interference-aware receiver. Typically, there are two types of detectors dealing with interference, known as enhanced interference rejection combining (eIRC) and symbol-level interference ca
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
On Divergence Approximations For Unsupervised Training Of Deep Denoisers Based On Stein’S Unbiased Risk Estimator
Recently, there have been several works on unsupervised learning for training deep learning based denoisers without clean images. Approaches based on Stein's unbiased risk estimator (SURE) have shown promising results for training Gaussian deep denoisers.
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A New Perspective For Flexible Feature Gathering In Scene Text Recognition Via Character Anchor Pooling
Irregular scene text recognition has attracted much attention from the research community, mainly due to the complexity of shapes of text in natural scene. However, recent methods either rely on shape-sensitive modules such as bounding box regression, or
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Scalable Kernel Learning Via The Discriminant Information
Kernel approximation methods create explicit, low-dimensional kernel feature maps to deal with the high computational and memory complexity of standard techniques. This work studies a supervised kernel learning methodology to optimize such mappings. We ut
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Optimal Laplacian Regularization For Sparse Spectral Community Detection
Regularization of the classical Laplacian matrices was empirically shown to improve spectral clustering in sparse networks. It was observed that small regularizations are preferable, but this point was left as a heuristic argument. In this paper we formal
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Quantized Tensor Robust Principal Component Analysis
High-dimensional data structures, known as tensors, are fundamental in many applications, including multispectral imaging and color video processing. Compression of such huge amount of multidimensional data collected over time is of paramount importance,
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Separable Optimization For Joint Blind Deconvolution And Demixing
Blind deconvolution and demixing is the problem of reconstructing convolved signals and kernels from the sum of their convolutions. This problem arises in many applications, such as blind MIMO. In this work, we present a separable approach to blind deconv
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Unsupervised Pre-Training Of Bidirectional Speech Encoders Via Masked Reconstruction
We propose an approach for pre-training speech representations via a masked reconstruction loss. Our pre-trained encoder networks are bidirectional and can therefore be used directly in typical bidirectional speech recognition models. The pre-trained netw
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Combining Cgan And Mil For Hotspot Segmentation In Bone Scintigraphy
Bone scintigraphy is widely used to diagnose bone tumor and metastasis. Accurate hotspot segmentation from bone scintigraphy is of great importance for tumor metastasis diagnosis. In this paper, we propose a new framework to detect and extract hotspots in
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Rev-Ae: A Learned Frame Set For Image Reconstruction
Reversible residual network naturally extends the linear lifting scheme with no theoretic guarantee. In this paper, we propose a reversible autoencoder (Rev-AE) with this extended non-linear lifting scheme to improve image reconstruction. Nonlinear predic
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Multitask Learning For Darpa Lorelei’S Situation Frame Extraction Task
This paper describes a novel approach of multitask learning for an end-to-end optimization technique for document classification. The application motivation comes from the need to extract "Situation Frames (SF)" from a document within the context of DARPA
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Disentangled Multidimensional Metric Learning For Music Similarity
Music similarity search is useful for a variety of creative tasks such as replacing one music recording with another recording with a similar "feel", a common task in video editing. For this task, it is typically necessary to define a similarity metric to
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Improving End-To-End Speech Synthesis With Local Recurrent Neural Network Enhanced Transformer
Although Transformer based neural end-to-end TTS model has demonstrated extreme effectiveness in capturing long-term dependencies and achieved state-of-the-art performance, it still suffers from two problems. 1) limited ability to model sequential and loc
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Finite Sample Deviation And Variance Bounds For First Order Autoregressive Processes
In this paper, we study finite-sample properties of the least squares estimator in first order autoregressive processes. By leveraging a result from decoupling theory, we derive upper bounds on the probability that the estimate deviates by at least a posi
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Controllable Time-Delay Transformer For Real-Time Punctuation Prediction And Disfluency Detection
With the increased applications of automatic speech recognition (ASR) in recent years, it is essential to automatically insert punctuation marks and remove disfluencies in transcripts, to improve the readability of the transcripts as well as the performan
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Drss-Based Localisation Using Weighted Instrumental Variables And Selective Power Measurement
Differential received signal strength (DRSS) provides a practical means of localisation for wireless sensor networks. Closed-form location estimators based on a linearised propagation path loss model are computationally efficient and hence suitable for wi
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Multi-Task Learning For Voice Trigger Detection
We describe the design of a voice trigger detection system for smart speakers. We address two major challenges. The first is that the detectors are deployed in complex acoustic environments with external noise and loud playback by the device itself. Secon
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Learning Graph Influence From Social Interactions
In social learning, agents form their opinions or beliefs about certain hypotheses by exchanging local information. This work considers the recent paradigm of weak graphs, where the network is partitioned into sending and receiving components, with the fo
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Robustness Assessment Of Automatic Reinke’S Edema Diagnosis Systems
In the past few years there has been a great interest in computer aided diagnosis research. In the field of voice quality assessment, signal processing gives us tools to analyze and extract numeric characteristics describing the analyzed signal. These fea
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Deep Product Quantization Module For Efficient Image Retrieval
Product Quantization (PQ) is one of the most popular Approximate Nearest Neighbor (ANN) methods for large-scale image retrieval, bringing better performance than hashing based methods. In recent years, several works extend the hard quantization to soft qu
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Motion Feedback Design For Video Frame Interpolation
This paper introduces a feedback-based approach to interpolate video frames involving small and fast-moving objects. Unlike the existing feedforward-based methods that estimate optical flow and synthesize in-between frames sequentially, we introduce a mot
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Global And Local Discriminative Patches Exploiting For Action Recognition
Recent human action recognition models mainly focus on exploiting human features, such as pose or skeleton features. However, due to the ignoring of interactive or related scenes exploiting, most of these methods cannot achieve good enough performance. In
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Approximate Inference By Kullback-Leibler Tensor Belief Propagation
Probabilistic programming provides a structured approach to signal processing algorithm design. The design task is formulated as a generative model, and the algorithm is derived through automatic inference. Efficient inference is a major challenge; e.g.,
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Enhanced Safety Of Autonomous Driving By Incorporating Terrestrial Signals Of Opportunity
A receiver autonomous integrity monitoring (RAIM)-based frame- work for autonomous ground vehicle (AGV) navigation is developed. This framework aims to incorporate terrestrial signals of opportunity (SOPs) alongside GPS signals to provide tight horizontal
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Meta Metric Learning For Highly Imbalanced Aerial Scene Classification
Class imbalance is an important factor that affects the performance of deep learning models used for remote sensing scene classification. In this paper, we propose a random fine-tuning meta metric learning model (RF-MML) to address this problem. Derived f
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Real-Time Hand Gesture Recognition Using Temporal Muscle Activation Maps Of Multi-Channel Semg Signals
Accurate and real-time hand gesture recognition is highly beneficial for improving the control of advanced hand prosthesis. Surface Electromyography (sEMG) signals obtained from the forearm are widely used in this area. In this paper, we introduce a novel
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Neural Network Wiretap Code Design For Multi-Mode Fiber Optical Channels
The design of reliable and secure codes with finite block length is an important requirement for industrial machine type communications. In this work, we develop an autoencoder for the multi-mode fiber wiretap channel taking into account the error perform
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Monaural Speech Enhancement Using Intra-Spectral Recurrent Layers In The Magnitude And Phase Responses
Speech enhancement has greatly benefited from deep learning. Currently, the best performing deep architectures use long short-term memory (LSTM) recurrent neural networks (RNNs) to model short and long temporal dependencies. These approaches, however, und
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Frame-Level Mmi As A Sequence Discriminative Training Criterion For Lvcsr
In this work we present frame-level maximum mutual information (MMI) as a novel sequence discriminative training criterion for hybrid HMM-DNN acoustic models. Compared to the standard, sequence-level MMI criterion we show that frame-level MMI has increase
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Self-Attentive Sentimental Sentence Embedding For Sentiment Analysis
We propose the use of a word-level sentiment bidirectional LSTM in tandem with the self-attention mechanism for sentence-level sentiment prediction. In addition to the pro- posed model, we also present a finance report dataset for sentence-level financial
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Fast And High-Quality Singing Voice Synthesis System Based On Convolutional Neural Networks
The present paper describes singing voice synthesis based on convolutional neural networks (CNNs). Singing voice synthesis systems based on deep neural networks (DNNs) are currently being proposed and are improving the naturalness of synthesized singing v
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Exploring A Zero-Order Direct Hmm Based On Latent Attention For Automatic Speech Recognition
In this paper, we study a simple yet elegant latent variable attention model for automatic speech recognition (ASR) which enables an integration of attention sequence modeling into the direct hidden Markov model (HMM) concept. We use a sequence of hidden
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Multi-Label Sound Event Retrieval Using A Deep Learning-Based Siamese Structure With A Pairwise Presence Matrix
Realistic recordings of soundscapes often have multiple sound events co-occurring, such as car horns, engine and human voices. Sound event retrieval, is a type of content-based search aiming at finding audio samples, similar to an audio query based on the
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Multi-Task Learning Via Sa-Fpn And Ej-Head
As a concise framework, Mask R-CNN achieves promising performance in object detection and instance segmentation. However, there is room for improvement in two aspects. One is that performing multi-task prediction needs more credible feature extraction and
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Zero-Crossing Precoding With Maximum Distance To The Decision Threshold For Channels With 1-Bit Quantization And Oversampling
Low-resolution devices are promising for systems that demand low energy consumption and low complexity as required in IoT systems. In this study, we propose a novel waveform for bandlimited channels with 1-bit quantization and oversampling at the receiver