Dong Wang

GNSS/Low-Cost MEMS-INS Integration Using Variational Bayesian Adaptive Cubature Kalman Smoother and Ensemble Regularized ELM

2015 · Mathematical Problems in Engineering

Among the inertial navigation system (INS) devices used in land vehicle navigation (LVN), low-cost microelectromechanical systems (MEMS) inertial sensors have received more interest for bridging global navigation satellites systems (GNSS) signal failures because of their …

Application and Analysis for Surge Arrester on Lightning Protection of Distribution Network

2015 · MATEC Web of Conferences

In order to effectively reduce lightning stroke outage rate, effect of lightning protection with surge arrester on transmission line has been generally acknowledged relative to other lightning protection measures. This article introduces in such aspects …

Deep Factorization for Speech Signal

2017 · arXiv (Cornell University)

Speech signals are complex intermingling of various informative factors, and this information blending makes decoding any of the individual factors extremely difficult. A natural idea is to factorize each speech frame into independent factors, though …

Entropic uncertainty relations for Markovian and non-Markovian processes under a structured bosonic reservoir

2017 · arXiv (Cornell University)

The uncertainty relation is a fundamental limit in quantum mechanics and is of great importance to quantum information processing as it relates to quantum precision measurement. Due to interactions with the surrounding environment, a quantum …

Memory-augmented Neural Machine Translation

2017

Neural machine translation (NMT) has achieved notable success in recent times, however it is also widely recognized that this approach has limitations with handling infrequent words and word pairs. This paper presents a novel memoryaugmented …

VAE-based Domain Adaptation for Speaker Verification

2019 · arXiv (Cornell University)

Deep speaker embedding has achieved satisfactory performance in speaker verification. By enforcing the neural model to discriminate the speakers in the training set, deep speaker embedding (called `x-vectors`) can be derived from the hidden layers. …

Transmitting Frequency Selection for HF Radar based on Convolutional Deep Belief Network

2019

This paper proposes a transmitting frequency selection method for HF radar based on convolutional deep belief network (CDBN), which is applied to select relatively quiet frequency band for radar in order to improve the detection …

Graph Representation Learning for Merchant Incentive Optimization in Mobile Payment Marketing

2019

Mobile payment such as Alipay has been widely used in our daily lives. To further promote the mobile payment activities, it is important to run marketing campaigns under a limited budget by providing incentives such …

The Evolution of Code Review Research: A Systematic Mapping Study

2019 · arXiv (Cornell University)

Code Review (CR) is a cornerstone for Quality Assurance within development teams. Also known as software inspections and walk-throughs, traditional CR involved time-consuming processes, which is different from more lightweight contemporary forms used today. In …

Graph Representation Learning for Merchant Incentive Optimization in Mobile Payment Marketing

2020 · arXiv (Cornell University)

Mobile payment such as Alipay has been widely used in our daily lives. To further promote the mobile payment activities, it is important to run marketing campaigns under a limited budget by providing incentives such …

AP19-OLR Challenge: Three Tasks and Their Baselines

2019

This paper introduces the fourth oriental language recognition (OLR) challenge AP19-OLR, including the data profile, the tasks and the evaluation principles. The OLR challenge has been held successfully for three consecutive years, along with APSIPA …

Neural Discriminant Analysis for Deep Speaker Embedding

2020 · arXiv (Cornell University)

Probabilistic Linear Discriminant Analysis (PLDA) is a popular tool in open-set classification/verification tasks. However, the Gaussian assumption underlying PLDA prevents it from being applied to situations where the data is clearly non-Gaussian. In this paper, …

Blockchain-based IoT device identification and management in 5G smart grid

2021 · EURASIP Journal on Wireless Communications and Networking

Abstract This work investigates the unified coding and identification of smart grid IoT devices, as more and more IoT devices in smart grid need to be managed and controlled. We combine blockchain technology with 5G …

WANA: Symbolic Execution of Wasm Bytecode for Extensible Smart Contract Vulnerability Detection

2021 · 2021 IEEE 21st International Conference on Software Quality, Reliability and Security (QRS)

Many popular blockchain platforms support smart contracts for building decentralized applications. However, the vulnerabilities within smart contracts have demonstrated to lead to serious financial loss to their end users. In particular, the smart contracts on …

QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive Adaptation

2022 · arXiv (Cornell University)

Question answering (QA) has recently shown impressive results for answering questions from customized domains. Yet, a common challenge is to adapt QA models to an unseen target domain. In this paper, we propose a novel …

A Glance is Enough: Extract Target Sentence By Looking at A keyword

2023 · arXiv (Cornell University)

This paper investigates the possibility of extracting a target sentence from multi-talker speech using only a keyword as input. For example, in social security applications, the keyword might be "help", and the goal is to …

Neural Scoring: A Refreshed End-to-End Approach for Speaker Recognition in Complex Conditions

2024 · arXiv (Cornell University)

Modern speaker verification systems primarily rely on speaker embeddings, followed by verification based on cosine similarity between the embedding vectors of the enrollment and test utterances. While effective, these methods struggle with multi-talker speech due …

Transferable Sequential Recommendation via Vector Quantized Meta Learning

2024 · arXiv (Cornell University)

While sequential recommendation achieves significant progress on capturing user-item transition patterns, transferring such large-scale recommender systems remains challenging due to the disjoint user and item groups across domains. In this paper, we propose a vector …

A Multi-Task Based Clustering Personalized Federated Learning Method

2024 · Big Data Mining and Analytics

Federated Learning (FL) is a framework for machine learning on a large-scale distributed dataset, enabling the training of a collaborative model across multiple parties while preserving the privacy of user data. However, in cases where …

A Hardware Architecture for Shared Residuals and Simplified Symmetric-PWL-Based GELU

2024

In this paper, we propose an innovative hardware acceleration scheme to optimize key components of Visual Transformer (ViT) and similar models. It features two main innovations. The first is a shared residual mechanism that integrates …

HA-BNN: Hardware-Aware Binary Neural Networks for Efficient Inference

2024

Binary Neural Networks (BNNs) use 1-bit weights and activations, replacing complex matrix multiplications with XNOR and bitcount operations, leading to a notable decrease in memory needs. It is worth highlighting that current BNNs commonly integrate …

Relation Classification via Recurrent Neural Network

2015 · arXiv (Cornell University)

Deep learning has gained much success in sentence-level relation classification. For example, convolutional neural networks (CNN) have delivered competitive performance without much effort on feature engineering as the conventional pattern-based methods. Thus a lot of …

THCHS-30 : A Free Chinese Speech Corpus

2015 · arXiv (Cornell University)

Speech data is crucially important for speech recognition research. There are quite some speech databases that can be purchased at prices that are reasonable for most research institutes. However, for young people who just start …

Normalized Word Embedding and Orthogonal Transform for Bilingual Word Translation

2015

Word embedding has been found to be highly powerful to translate words from one language to another by a simple linear transform. However, we found some inconsistence among the objective functions of the embedding and …

Chinese song iambics generation with neural attention-based model

2016 · arXiv (Cornell University)

Learning and generating Chinese poems is a charming yet challenging task. Traditional approaches involve various language modeling and machine translation techniques, however, they perform not as well when generating poems with complex pattern constraints, for …

Transfer learning for speech and language processing

2015

Transfer learning is a vital technique that generalizes models trained for one setting or task to other settings or tasks. For example in speech recognition, an acoustic model trained for one language can be used …

Flexible and Creative Chinese Poetry Generation Using Neural Memory

2017

Jiyuan Zhang, Yang Feng, Dong Wang, Yang Wang, Andrew Abel, Shiyue Zhang, Andi Zhang. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2017.

An Overview of End-to-End Automatic Speech Recognition

2019 · Symmetry

Automatic speech recognition, especially large vocabulary continuous speech recognition, is an important issue in the field of machine learning. For a long time, the hidden Markov model (HMM)-Gaussian mixed model (GMM) has been the mainstream …