• Publications
  • Influence
Deep Speaker: an End-to-End Neural Speaker Embedding System
TLDR
We present Deep Speaker, a neural speaker embedding system that maps utterances to a hypersphere where speaker similarity is measured by cosine similarity. Expand
  • 239
  • 37
  • PDF
Basic Performance Measurements of the Intel Optane DC Persistent Memory Module
TLDR
This work comprises the first in-depth, scholarly, performance review of Intel's Optane DC Persistent Memory Module, exploring its capabilities as a main memory device, and as persistent, byte-addressable memory exposed to user-space applications. Expand
  • 130
  • 26
  • PDF
Deep Metric Learning with Angular Loss
TLDR
In this paper, we propose a novel angular loss, which takes angle relationship into account, for learning better similarity metric. Expand
  • 196
  • 23
  • PDF
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
TLDR
Selective transfer units are incorporated with encoder-decoder to adaptively select and modify encoder feature for enhanced attribute editing. Expand
  • 58
  • 20
  • PDF
Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation
TLDR
We propose a novel framework to jointly extract multiple event triggers and arguments by introducing syntactic shortcut arcs to enhance information flow and attention-based graph convolution networks to model graph information. Expand
  • 67
  • 19
  • PDF
Fully Convolutional Attention Localization Networks: Efficient Attention Localization for Fine-Grained Recognition
TLDR
We introduce a reinforcement learning-based fully convolutional attention localization network to adaptively select multiple task-driven visual attention regions for fine-grained recognition. Expand
  • 60
  • 16
  • PDF
A Revised Discrete Particle Swarm Optimization for Cloud Workflow Scheduling
TLDR
In this paper, a Revised Discrete Particle Swarm Optimization (RDPSO) is proposed to schedule applications among cloud services that takes both data transmission cost and computation cost into account. Expand
  • 200
  • 12
  • PDF
Hybrid delay scan: a low hardware overhead scan-based delay test technique for high fault coverage and compact test sets
TLDR
A novel scan-based delay test approach, referred as the hybrid delay scan, is proposed in this paper. Expand
  • 87
  • 12
  • PDF
Quantitative imaging of energy expenditure in human brain
TLDR
In this study, we applied an advanced in vivo(31)P MRS imaging approach to obtain regional cerebral metabolic rates of high-energy phosphate reactions catalyzed by ATPase (CMR(ATPase)) and creatine kinase ( CMR(CK) in pure gray mater (GM) and white mater (WM), respectively. Expand
  • 135
  • 11
An empirical study on software defect prediction with a simplified metric set
TLDR
We validate the feasibility of the predictor built with a simplified metric set for software defect prediction in different scenarios, and investigate practical guidelines for the choice of training data, classifier and metric subset of a given project. Expand
  • 147
  • 11
  • PDF