Showing 151 - 200 of 1951
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Distilling Attention Weights For Ctc-Based Asr Systems
We present a novel training approach for connectionist temporal classification (CTC) -based automatic speech recognition (ASR) systems. CTC models are promising for building both a conventional acoustic model and an end-to-end (E2E) ASR model. However, CT
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Estimation Of Post-Nonlinear Causal Models Using Autoencoding Structure
Discovering causal relations in complex systems is an important problem in many research fields. To describe such systems involving nonlinear causal relations, the post-nonlinear (PNL) causal model has been proposed. However, despite its identifiability,
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Robust Low Rate Speech Coding Based On Cloned Networks And Wavenet
Rapid advances in machine-learning based generative modeling of speech make its use in speech coding attractive. However, the current performance of such models drops rapidly with noise contamination of the input, preventing use in practical applications.
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
3D Deformation Signature For Dynamic Face Recognition
This work proposes a novel 3D Deformation Signature (3DS) to represent a 3D deformation signal for 3D Dynamic Face Recognition. 3DS is computed given a non-linear 6D-space representation which guarantees physically plausible 3D deformations. A unique defo
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
An Analysis Of Speech Enhancement And Recognition Losses In Limited Resources Multi-Talker Single Channel Audio-Visual Asr
In this paper, we analyzed how audio-visual speech enhancement can help to perform the ASR task in a cocktail party scenario. Therefore we considered two simple end-to-end LSTM-based models that perform single-channel audiovisual speech enhancement and ph
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Fully-Neural Approach To Heavy Vehicle Detection On Bridges Using A Single Strain Sensor
Bridge weigh-in-motion (BWIM) is a technique for detecting heavy vehicles that may cause serious damage to real bridges. BWIM is realized by analyzing the strain signals observed at places on the bridge in terms of bridge-component responses to the axle l
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Energy Efficient Acceleration Of Floating Point Applications Onto Cgra
In this paper, we propose a novel CGRA architecture and associated compilation flow supporting both integer and floating-point computations for energy efficient acceleration of DSP applications. Experimental results show that the proposed accelerator achi
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Overlapped State Hidden Semi-Markov Model For Grouped Multiple Sequences
Efficient analysis of multiple sequential data is becoming necessary for identifying sequential patterns of multiple objects of interest. This analysis has major practical and technical importance because finding such patterns necessitates extraction and
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Anomalydae: Dual Autoencoder For Anomaly Detection On Attributed Networks
Anomaly detection on attributed networks aims at finding nodes whose patterns deviate significantly from the majority of reference nodes, which is pervasive in many applications such as network intrusion detection and social spammer detection. However, mo
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Improving The Performance Of Transformer Based Low Resource Speech Recognition For Indian Languages
The recent success of the Transformer based sequence-to-sequence framework for various Natural Language Processing tasks has motivated its application to Automatic Speech Recognition. In this work, we explore the application of Transformers on low resourc
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
On The Byzantine Robustness Of Clustered Federated Learning
Federated Learning (FL) is currently the most widely adopted framework for collaborative training of (deep) machine learning models under privacy constraints. Albeit it's popularity, it has been observed that Federated Learning yields suboptimal results i
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Dynamic Channel Pruning For Correlation Filter Based Object Tracking
Fusion of multi-channel representations has played a crucial role in the success of correlation filter (CF) based trackers. But, all channels do not contain useful information for target localization at every frame. During challenging scenarios, ambiguous
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Patch-Level Selection And Breadth-First Prediction Strategy For Reversible Data Hiding
A core work in reversible data hiding is designing an embedding method enabling the hider to take advantages of smooth elements as many as possible while the detection procedure for marked elements is invertible to the receiver. It motivates us to introdu
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Frequency-Dependent Directional Feedback Delay Network
A recent publication introduced the Directional Feedback Delay Network, a parametric artificial reverberation algorithm capable of producing direction-dependent energy decay. This method extends the capabilities of Feedback Delay Networks by using multich
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Auglabel: Exploiting Word Representations To Augment Labels For Face Attribute Classification
Augmenting data in image space (eg. flipping, cropping etc) and activation space (eg. dropout) are being widely used to regularise deep neural networks and have been successfully applied on several computer vision tasks. Unlike previous works, which are m
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Energan: A Generative Adversarial Network For Energy Disaggregation
An efficient, appliance-level approach for energy disaggregation, exploiting the benefits of Generative Adversarial Networks, is presented. The concept of adversarial training supports the creation of fine tuned dissagregators, which produce more detailed
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Wirtinger Flow Algorithms For Phase Retrieval From Binary Measurements
We consider the problem of Binary Phase Retrieval, wherein we attempt to recover signals from their quadratic measurements, which are further encoded as +1 or ?1 depending on whether they exceed a threshold or not. Binary encoding is the extreme case of q
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Optimal Design Of Energy-Efficient Cell-Free Massive Mimo: Joint Power Allocation And Load Balancing
A large-scale distributed antenna system that serves the users by coherent joint transmission is called Cell-free Massive MIMO (multiple input multiple output). For a given user set, only a subset of the access points (APs) is likely needed to satisfy the
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Fusion Approaches For Emotion Recognition From Speech Using Acoustic And Text-Based Features
In this paper, we study different approaches for classifying emotions from speech using acoustic and text-based features. We propose to obtain contextualized word embeddings with BERT to represent the information contained in speech transcriptions and sho
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Multi-Branch Learning For Weakly-Labeled Sound Event Detection
There are two sub-tasks implied in the weakly-supervised SED: audio tagging and event boundary detection. Current methods which combine multi-task learning with SED requires annotations both for these two sub-tasks. Since there are only annotations for au
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
H-Vectors: Utterance-Level Speaker Embedding Using A Hierarchical Attention Model
In this paper, a hierarchical attention network is proposed to generate utterance-level embeddings (H-vectors) for speaker identification and verification. Since different parts of an utterance may have different contributions to speaker identities, the u
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
How Confident Are You? Exploring The Role Of Fillers In The Automatic Prediction Of A Speaker’s Confidence
"Fillers", example "um" in English, have been linked to the "Feeling of Another's Knowing (FOAK)" or the listener's perception of a speaker?s expressed confidence. Yet, in Spoken Language Processing (SLP) they remain unexplored, or overlooked as noise. We
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
A Comparative Study Of Estimating Articulatory Movements From Phoneme Sequences And Acoustic Features
Unlike phoneme sequences, movements of speech articulators (lips, tongue, jaw, velum) and the resultant acoustic signal are known to encode not only the linguistic message but also carry para-linguistic information. While several works exist for estimatin
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Distributed Tensor Completion Over Networks
The aim of this paper is to propose a novel distributed strategy for tensor completion, where (partial) data are collected over a network of agents with sparse, but connected, topology. The method hinges on the canonical polyadic decomposition, also known
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Privacy-Preserving Phishing Web Page Classification Via Fully Homomorphic Encryption
This work introduces a fast and lightweight homomorphic-encryption pipeline that enables privacy-preserving machine learning for phishing web page recognition. The primary goals are to use visual features to train an accurate model and to implement an inf
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Spatially Adaptive Intra Mode Pre-Selection For Erp 360 Video Coding
In this work, we propose a spatially adaptive HEVC intra mode pre-selection for equirectangular (ERP) 360 video coding. The proposed technique exploits the spatial characteristics of 360 video in the ERP projection to reduce the complexity of intra predic
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Bba-Net: A Bi-Branch Attention Network For Crowd Counting
In the field of crowd counting, the current mainstream CNN-based regression methods simply extract the density information of pedestrians without finding the position of each person. This makes the output of the network often found to contain incorrect re
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Incorporating Written Domain Numeric Grammars Into End-To-End Contextual Speech Recognition Systems For Improved Recognition Of Numeric Sequences
Accurate recognition of numeric sequences is crucial for many contextual speech recognition applications. For example, a user might create a calendar event and be prompted by a virtual assistant for the time, date, and duration of the event. We propose a
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Within-Sample Variability-Invariant Loss For Robust Speaker Recognition Under Noisy Environments
Despite the significant improvements in speaker recognition enabled by deep neural networks, unsatisfactory performance persists under noisy environments. In this paper, we train the speaker embedding network to learn the ``clean'' embedding of the noisy
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Low Rank Activations For Tensor-Based Convolutional Sparse Coding
In this article, we propose to extend the classical Convolutional Sparse Coding model (CSC) to multivariate data by introducing a new tensor CSC model that enforces sparsity and low-rank constraint on the activations. The advantages of this model are thre
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Stock Movement Prediction That Integrates Heterogeneous Data Sources Using Dilated Causal Convolution Networks With Attention
The purpose of this research is to develop a high performing model for stock movement prediction utilizing financial indicators and news data. Until recently, the majority of prediction models have employed only the financial indicators, but they possess
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Exploring Pre-Training With Alignments For Rnn Transducer Based End-To-End Speech Recognition
Recently, the recurrent neural network transducer (RNN-T) architecture has become an emerging trend in end-to-end automatic speech recognition research due to its advantages of being capable for online streaming speech recognition. However, RNN-T training
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Fast Direction-Of-Arrival Estimation Of Multiple Targets Using Deep Learning And Sparse Arrays
In this work, we focus on improving the Direction-of-Arrival (DoA) estimation of multiple targets/sources from a small number of snapshots. Estimation via the sample covariance matrix is known to perform poorly, since the true manifold structure is not re
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Cra: A Generic Compression Ratio Adapter For End-To-End Data-Driven Image Compressive Sensing Reconstruction Frameworks
End-to-end data-driven image compressive sensing reconstruction (EDCSR) frameworks achieve state-of-the-art reconstruction performance in terms of reconstruction speed and accuracy. However, due to their end-to-end nature, existing EDCSR frameworks can no
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Slow-Time Mimo-Fmcw Automotive Radar Detection With Imperfect Waveform Separation
This paper considers object detection in the case of imperfect waveform separation, in the context of automotive radars that employ a slow-time MIMO-FMCW signaling scheme. We develop an explicit signal model that accounts for waveform separation residuals
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Accurate 6D Object Pose Estimation By Pose Conditioned Mesh Reconstruction
Current 6D object pose estimation methods consist of Deep Convolutional Neural Networks fully optimized for a single object but with its architecture standardized among objects with different shapes. In contrast to previous works, we explicitly exploit ea
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Low-Frequency Compensated Synthetic Impulse Responses For Improved Far-Field Speech Recognition
We propose a method for generating low-frequency compensated synthetic impulse responses that improve the performance of far-field speech recognition systems trained on artificially augmented datasets. We design linear-phase filters that adapt the simulat
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Channel Charting: An Euclidean Distance Matrix Completion Perspective
Channel charting (CC) is an emerging machine learning framework that aims at learning lower-dimensional representations of the radio geometry from collected channel state information (CSI) in an area of interest, such that spatial relations of the represe
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Libri-Adapt: A New Speech Dataset For Unsupervised Domain Adaptation
This paper introduces a new dataset, Libri-Adapt, to support unsupervised domain adaptation research on speech recognition models. Built on top of the LibriSpeech corpus, Libri-Adapt contains 7200 hours of English speech recorded on mobile and embedded-sc
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Label Reuse For Efficient Semi-Supervised Learning
In this paper, we propose a new learning strategy for semi-supervised deep learning algorithms, called label reuse, aiming to significantly reduce the expensive computational cost of pseudo label generation and the like for each unlabeled training instanc
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
End-To-End Non-Negative Autoencoders For Sound Source Separation
Discriminative models for source separation have recently been shown to produce impressive results. However, when operating on sources outside of the training set, these models can not perform as well and are cumbersome to update. Classical methods like N
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Retrieving Vocal-Tract Resonance And Anti-Resonance From High-Pitched Vowels Using A Rahmonic Subtraction Technique
Vocal tract resonances give rise to core spectral information of speech signals. Linear prediction and cepstral methods are widely used for this purpose. However, both approaches are prone to fail as the fundamental frequency (F0) rises. In this study, a
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Passive Intelligent Surface Assisted Mimo Powered Sustainable Iot
Lately, Passive Intelligent Surfaces (PIS) are being recognized to play an important role in meeting the timely demand of low-cost green sustainable Internet of Things (IoT). In this paper, we focus on maximizing the sum received power among the energy ha
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
End-To-End Code-Switching Tts With Cross-Lingual Language Model
Code-switching text-to-speech (TTS) aims to enable a system to speak two languages with a single voice and in the same utterance. In this paper, we propose to incorporate cross-lingual word embedding into an end-to-end TTS system, to improve the voice ren
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Lai-Net: Local-Ancestry Inference With Neural Networks
Local-ancestry inference (LAI), also referred to as ancestry deconvolution, provides high-resolution ancestry estimation along the human genome. In both research and industry, LAI is emerging as a critical step in personalized DNA sequence analysis with a
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Atomic Norm Based Localization Of Far-Field And Near-Field Signals With Generalized Symmetric Arrays
Most localization methods for mixed far-field (FF) and nearfield (NF) sources are based on uniform linear array (ULA) rather than sparse linear array (SLA). In this paper, we propose a localization method for mixed FF and NF sources based on the generaliz
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Training Keyword Spotters With Limited And Synthesized Speech Data
With the rise of low power speech-enabled devices, there is a growing demand to quickly produce models for recognizing arbitrary sets of keywords. As with many machine learning tasks, one of the most challenging parts in the model creation process is obta
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Classify And Explain: An Interpretable Convolutional Neural Network For Lung Cancer Diagnosis
The deep network-based computer-aided diagnosis systems have encountered many difficulties in practical applications because of its "black box" feature. The crux of the problem is that these models should be explainable ? the model should provide doctors
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Foreground Signature Extraction For An Intimate Mixing Model In Hyperspectral Image Classification
The hyperspectral unmixing problem arises in remote sensing, chemometrics, and biomedical engineering applications. The spectral signature of a single pixel in a hyperspectral cube can be represented as a non-negative combination of non-negative signature