Skip to main navigation
Skip to search
Skip to main content
Northwestern Polytechnical University Home
English
中文
Home
Profiles
Research units
Research output
Search by expertise, name or affiliation
View Scopus Profile
Xie Lei
Professor
School of Computer Science
h-index
6391
Citations
38
h-index
Calculated based on number of publications stored in Pure and citations from Scopus
2002
2025
Research activity per year
Overview
Fingerprint
Network
Research output
(439)
Similar Profiles
(5)
Fingerprint
Dive into the research topics where Lei Xie is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Computer Science
Speech Recognition
100%
Speech Synthesis
47%
Experimental Result
40%
Broadcast News
39%
Text To Speech
27%
Speech Enhancement
25%
Deep Neural Network
24%
Training Data
23%
Neural Network
22%
Adversarial Machine Learning
20%
Speech Recognition System
19%
Expressive Speech
18%
Speaker Verification
18%
Language Modeling
17%
Recurrent Neural Network
16%
Attention (Machine Learning)
14%
Synthetic Speech
13%
Long Short-Term Memory Network
13%
Regularization
13%
Bidirectional Long Short-Term Memory Network
13%
Speaker Diarization
12%
Decision Tree
11%
Data Augmentation
11%
Superior Performance
10%
Contextual Information
9%
Speech Generation
9%
Visual Feature
9%
Robust Speech Recognition
9%
Open Source
9%
Acoustic Feature
9%
Multitask Learning
9%
Subjective Evaluation
8%
Language Specific
8%
Laplace Operator
7%
False Alarm Rate
7%
Boundary Detection
7%
Seq2Seq
7%
de-noising
7%
Conditional Random Field
7%
Representation Learning
7%
Voice Cloning
7%
False Rejection Rate
7%
Inference Process
7%
Word Error Rate
7%
Training Model
6%
Recognition Performance
6%
Discriminator
5%
Fundamental Frequency
5%
Sentence Boundary
5%
Diffusion Model
5%
Engineering
Experimental Result
23%
Deep Neural Network
18%
Speech Enhancement
18%
Similarity
14%
Error Rate
13%
Broadcast News
11%
Recurrent Neural Network
11%
Automatic Speech Recognition
11%
Multichannel
11%
Continuous Speech Recognition
11%
False Alarm Rate
10%
Neural Network Approach
9%
False Rejection
9%
Speech Signal
8%
Regularization
8%
Reverberation
8%
Joints (Structural Components)
7%
Learning Task
7%
Speech Data
6%
Signal Band
6%
Long Short-Term Memory
6%
Objective Evaluation
6%
Robust Speech Recognition
6%
Acoustic Feature
6%
Head-Related Transfer Function
5%
Transducer
5%
False Alarm
5%
Sound Source
5%
Recurrent Network
5%
