b'Yang Zhang'

Global Rhythm Style Transfer Without Text Transcriptions

Prosody plays an important role in characterizing the style of a speaker...
06/16/2021 ∙ by Kaizhi Qian, et al. ∙ 6 ∙ share

read it
Voting for the right answer: Adversarial defense for speaker verification

Automatic speaker verification (ASV) is a well developed technology for ...
06/15/2021 ∙ by Haibin Wu, et al. ∙ 0 ∙ share

read it
Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators

While maximizing deep neural networks' (DNNs') acceleration efficiency r...
06/11/2021 ∙ by Yonggan Fu, et al. ∙ 0 ∙ share

read it
PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition

Recent work on speech self-supervised learning (speech SSL) demonstrated...
06/10/2021 ∙ by Cheng-I Jeff Lai, et al. ∙ 4 ∙ share

read it
Conversational Question Answering: A Survey

Question answering (QA) systems provide a way of querying the informatio...
06/02/2021 ∙ by Munazza Zaib, et al. ∙ 39 ∙ share

read it
SGD-QA: Fast Schema-Guided Dialogue State Tracking for Unseen Services

Dialogue state tracking is an essential part of goal-oriented dialogue s...
05/17/2021 ∙ by Yang Zhang, et al. ∙ 0 ∙ share

read it
Causal Intervention for Leveraging Popularity Bias in Recommendation

Recommender system usually faces popularity bias issues: from the data p...
05/13/2021 ∙ by Yang Zhang, et al. ∙ 0 ∙ share

read it
NeMo Inverse Text Normalization: From Development To Production

Inverse text normalization (ITN) converts spoken-domain automatic speech...
04/11/2021 ∙ by Yang Zhang, et al. ∙ 0 ∙ share

read it
Explaining COVID-19 and Thoracic Pathology Model Predictions by Identifying Informative Input Features

Neural networks have demonstrated remarkable performance in classificati...
04/01/2021 ∙ by Ashkan Khakzar, et al. ∙ 0 ∙ share

read it
Graph Unlearning

The right to be forgotten states that a data subject has the right to er...
03/27/2021 ∙ by Min Chen, et al. ∙ 23 ∙ share

read it
Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation

Panoptic segmentation presents a new challenge in exploiting the merits ...
03/27/2021 ∙ by Zixiang Zhou, et al. ∙ 0 ∙ share

read it
Node-Level Membership Inference Attacks Against Graph Neural Networks

Many real-world data comes in the form of graphs, such as social network...
02/10/2021 ∙ by Xinlei He, et al. ∙ 10 ∙ share

read it
Quantifying and Mitigating Privacy Risks of Contrastive Learning

Data is the key factor to drive the development of machine learning (ML)...
02/08/2021 ∙ by Xinlei He, et al. ∙ 6 ∙ share

read it
ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models

Inference attacks against Machine Learning (ML) models allow adversaries...
02/04/2021 ∙ by Yugeng Liu, et al. ∙ 0 ∙ share

read it
A Unified Light Framework for Real-time Fault Detection of Freight Train Images

Real-time fault detection for freight trains plays a vital role in guara...
01/31/2021 ∙ by Yang Zhang, et al. ∙ 15 ∙ share

read it
AT-BERT: Adversarial Training BERT for Acronym Identification Winning Solution for SDU@AAAI-21

Acronym identification focuses on finding the acronyms and the phrases t...
01/11/2021 ∙ by Danqing Zhu, et al. ∙ 0 ∙ share

read it
Unified Mandarin TTS Front-end Based on Distilled BERT Model

The front-end module in a typical Mandarin text-to-speech system (TTS) i...
12/31/2020 ∙ by Yang Zhang, et al. ∙ 0 ∙ share

read it
PrivSyn: Differentially Private Data Synthesis

In differential privacy (DP), a challenging problem is to generate synth...
12/30/2020 ∙ by Zhikun Zhang, et al. ∙ 0 ∙ share

read it
Mention Extraction and Linking for SQL Query Generation

On the WikiSQL benchmark, state-of-the-art text-to-SQL systems typically...
12/18/2020 ∙ by Jianqiang Ma, et al. ∙ 0 ∙ share

read it
The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models

The computer vision world has been re-gaining enthusiasm in various pre-...
12/12/2020 ∙ by Tianlong Chen, et al. ∙ 9 ∙ share

read it
Deep Network Perceptual Losses for Speech Denoising

Contemporary speech enhancement predominantly relies on audio transforms...
11/21/2020 ∙ by Mark R. Saddler, et al. ∙ 0 ∙ share

read it
A Survey on Contact Tracing: the Latest Advancements and Challenges

Infectious diseases are caused by pathogenic microorganisms, such as bac...
11/04/2020 ∙ by Ting Jiang, et al. ∙ 0 ∙ share

read it
Improving RNN transducer with normalized jointer network

Recurrent neural transducer (RNN-T) is a promising end-to-end (E2E) mode...
11/03/2020 ∙ by Mingkun Huang, et al. ∙ 0 ∙ share

read it
Dynamic latency speech recognition with asynchronous revision

In this work we propose an inference technique, asynchronous revision, t...
11/03/2020 ∙ by Mingkun Huang, et al. ∙ 0 ∙ share

read it
Squeezing value of cross-domain labels: a decoupled scoring approach for speaker verification

Domain mismatch often occurs in real applications and causes serious per...
10/27/2020 ∙ by Lantian Li, et al. ∙ 0 ∙ share

read it
Deep generative factorization for speech signal

Various information factors are blended in speech signals, which forms t...
10/27/2020 ∙ by Haoran Sun, et al. ∙ 0 ∙ share

read it
Double-Uncertainty Weighted Method for Semi-supervised Learning

Though deep learning has achieved advanced performance recently, it rema...
10/19/2020 ∙ by Yixin Wang, et al. ∙ 0 ∙ share

read it
Modality-Pairing Learning for Brain Tumor Segmentation

Automatic brain tumor segmentation from multi-modality Magnetic Resonanc...
10/19/2020 ∙ by Yixin Wang, et al. ∙ 0 ∙ share

read it
BioMegatron: Larger Biomedical Domain Language Model

There has been an influx of biomedical domain-specific language models, ...
10/12/2020 ∙ by Hoo-chang Shin, et al. ∙ 11 ∙ share

read it
Fuzzing Based on Function Importance by Attributed Call Graph

Fuzzing has become one of the important methods for vulnerability detect...
10/07/2020 ∙ by Wenshuo Wang, et al. ∙ 0 ∙ share

read it
Don't Trigger Me! A Triggerless Backdoor Attack Against Deep Neural Networks

Backdoor attack against deep neural networks is currently being profound...
10/07/2020 ∙ by Ahmed Salem, et al. ∙ 6 ∙ share

read it
BAAAN: Backdoor Attacks Against Autoencoder and GAN-Based Machine Learning Models

The tremendous progress of autoencoders and generative adversarial netwo...
10/06/2020 ∙ by Ahmed Salem, et al. ∙ 14 ∙ share

read it
Dual Attention Model for Citation Recommendation

Based on an exponentially increasing number of academic articles, discov...
10/01/2020 ∙ by Yang Zhang, et al. ∙ 35 ∙ share

read it
Privacy Analysis of Deep Learning in the Wild: Membership Inference Attacks against Transfer Learning

While being deployed in many critical applications as core components, m...
09/10/2020 ∙ by Yang Zou, et al. ∙ 7 ∙ share

read it
A Novel Software-based Multi-path RDMA Solutionfor Data Center Networks

In this paper we propose Virtuoso, a purely software-based multi-path RD...
09/01/2020 ∙ by Feng Tian, et al. ∙ 0 ∙ share

read it
A Fast and Robust BERT-based Dialogue State Tracker for Schema-Guided Dialogue Dataset

Dialog State Tracking (DST) is one of the most crucial modules for goal-...
08/27/2020 ∙ by Vahid Noroozi, et al. ∙ 10 ∙ share

read it
CCA: Exploring the Possibility of Contextual Camouflage Attack on Object Detection

Deep neural network based object detection hasbecome the cornerstone of ...
08/19/2020 ∙ by Shengnan Hu, et al. ∙ 7 ∙ share

read it
Scalable and Communication-efficient Decentralized Federated Edge Learning with Multi-blockchain Framework

The emerging Federated Edge Learning (FEL) technique has drawn considera...
08/10/2020 ∙ by Jiawen Kang, et al. ∙ 0 ∙ share

read it
Label-Leaks: Membership Inference Attack with Label

Machine learning (ML) has made tremendous progress during the past decad...
07/30/2020 ∙ by Zheng Li, et al. ∙ 31 ∙ share

read it
The Lottery Ticket Hypothesis for Pre-trained BERT Networks

In natural language processing (NLP), enormous pre-trained models like B...
07/23/2020 ∙ by Tianlong Chen, et al. ∙ 7 ∙ share

read it
PP-YOLO: An Effective and Efficient Implementation of Object Detector

Object detection is one of the most important areas in computer vision, ...
07/23/2020 ∙ by Xiang Long, et al. ∙ 31 ∙ share

read it
Deep Anomaly Detection for Time-series Data in Industrial IoT: A Communication-Efficient On-device Federated Learning Approach

Since edge device failures (i.e., anomalies) seriously affect the produc...
07/19/2020 ∙ by YI LIU, et al. ∙ 25 ∙ share

read it
Generating Visually Aligned Sound from Videos

We focus on the task of generating sound from natural videos, and the so...
07/14/2020 ∙ by Peihao Chen, et al. ∙ 0 ∙ share

read it
Learning Differential Diagnosis of Skin Conditions with Co-occurrence Supervision using Graph Convolutional Networks

Skin conditions are reported the 4th leading cause of nonfatal disease b...
07/13/2020 ∙ by Junyan Wu, et al. ∙ 34 ∙ share

read it
Design Space Exploration of Power Delivery For Advanced Packaging Technologies

In this paper, a design space exploration of power delivery networks is ...
07/10/2020 ∙ by Md Obaidul Hossen, et al. ∙ 0 ∙ share

read it
Cognitive Radio Network Throughput Maximization with Deep Reinforcement Learning

Radio Frequency powered Cognitive Radio Networks (RF-CRN) are likely to ...
07/07/2020 ∙ by Kevin Shen Hoong Ong, et al. ∙ 0 ∙ share

read it
Modality-Agnostic Attention Fusion for visual search with text feedback

Image retrieval with natural language feedback offers the promise of cat...
06/30/2020 ∙ by Eric Dodds, et al. ∙ 16 ∙ share

read it
Affinity Fusion Graph-based Framework for Natural Image Segmentation

This paper proposes an affinity fusion graph framework to effectively co...
06/24/2020 ∙ by Yang Zhang, et al. ∙ 8 ∙ share

read it
Does Non-COVID19 Lung Lesion Help? Investigating Transferability in COVID-19 CT Image Segmentation

Coronavirus disease 2019 (COVID-19) is a highly contagious virus spreadi...
06/23/2020 ∙ by Yixin Wang, et al. ∙ 2 ∙ share

read it
BadNL: Backdoor Attacks Against NLP Models

Machine learning (ML) has progressed rapidly during the past decade and ...
06/01/2020 ∙ by Xiaoyi Chen, et al. ∙ 0 ∙ share

read it

Yang Zhang

Featured Co-authors