跳至主導覽
跳至搜尋
跳過主要內容
國立中央大學 首頁
說明與常見問題
English
中文
首頁
人才檔案
研究單位
研究計畫
研究成果
資料集
榮譽/獲獎
學術活動
新聞/媒體
影響
按專業知識、姓名或所屬機構搜尋
智慧型照護互動系統－基於深度智能之口語處理技術(2/4)
Wang, Jia-Ching
(PI)
資訊工程學系
概覽
指紋
研究成果
(15)
指紋
探索此專案觸及的研究主題。這些標籤是根據基礎獎勵/補助款而產生。共同形成了獨特的指紋。
排序方式
重量
按字母排序
Keyphrases
Deep Learning
100%
Calcaneal Fracture
80%
Hierarchical Extreme Learning Machine (H-ELM)
80%
Speech Enhancement
80%
Data Augmentation
53%
State-of-the-art Techniques
50%
Sound Events
48%
Speaker Characterization
40%
Automated Classification
40%
Differential Data
40%
CT Images
40%
Speeded up Robust Features
40%
Speaker Embedding
40%
Sanders Classification
40%
Automated Detection
40%
Capsule Neural Network
40%
Image Dehazing
40%
Attention Block
40%
Retinal Edema
40%
Events on the Road
40%
Attention Model
40%
Convolutional Block Attention Module
40%
Spatial Pyramid Pooling
40%
Optical Coherence Tomography Images
40%
Convolutional Neural Network
40%
N-best
40%
Sparse Subspace
40%
Single-channel Speech Enhancement
40%
Event Retrieval
40%
Sound Event Recognition
40%
Sparse Coding
40%
Convolutional
40%
Joint Non-negative Matrix Factorization
40%
Dialogue State Tracking
40%
Speech Emotion Recognition
40%
Early Warning System
40%
Neural Network
40%
Audio-based
40%
Learning Data
40%
Data Representation
40%
Computed Tomography Images
40%
Speech Recognition
40%
Kullback-Leibler Divergence
40%
Robust Nonnegative Matrix Factorization
40%
Encoder
40%
Encoder-decoder
40%
Sound Event Detection
40%
Deep Q-network
40%
Hearing Impaired
40%
Speaker Recognition Evaluation
40%
Delayed Neural Networks
40%
Long Short-term Memory Neural Network
40%
Multi-task CNN
40%
Age Recognition
40%
Popular
40%
Number of Parameters
40%
Gender Recognition
40%
Deep Convolutional Neural Network (deep CNN)
38%
Training Data
33%
Automatic Speech Recognition
32%
Residual Network
30%
Sanders
30%
Deep Learning Model
30%
Calcaneus
30%
Decision Cost
26%
Chatbot
20%
3D Avatar
20%
Calcaneal
20%
Clear Image
20%
Overfitting
20%
Computer Use
20%
Medical Diagnosis
20%
Hazy Images
20%
Large Database
20%
BiSeNet
20%
Spatial Structure Information
20%
Semantic Image Segmentation
20%
People with Hearing Impairment
20%
Illness
20%
Network Attention
20%
Eight Class
20%
Existing Problems
20%
Dice Coefficient
20%
Spatial Contextual Information
20%
DeepLabv3+
20%
Spatial Structure
20%
Computer Vision
20%
Joint Dictionary Learning
20%
Network Classification
20%
Computer-aided Classification
20%
Principal Coordinate Analysis (PCoA)
20%
Training Image
20%
Device Interface
20%
Decoder
20%
Fracture Type
20%
Penalty Term
20%
Prediction Model
20%
Human-machine Interface
20%
Learning Approaches
20%
Training Methods
20%
Amount of Training
20%
Learned Dictionary
20%
Class Classification
20%
Learning Representations
20%
Android Platform
20%
Enhancement System
20%
Visual Information
20%
Environmental Sounds
20%
Gender Identification
20%
Age Identification
20%
Experiment Results
20%
Social Networks
20%
Lightweight Model
20%
Multimedia Services
20%
Multimodal Speech
17%
SC-CNN
16%
Utterance
16%
Tracking Accuracy
16%
Audio Information
15%
Score Combination
13%
Indian Institute of Technology
13%
Evaluation Task
13%
Front-end Features
13%
National Institute of Standards
13%
Kernel Design
13%
DCASE2017 Challenge
13%
Event Detection System
13%
Overlapping Objects
13%
Parallel Architecture
13%
Detection Accuracy
13%
Cone Constraints
13%
Systems-based
13%
Good Characteristics
13%
Error Rate
13%
Cost Function
13%
Constrained NMF
13%
Sparse Representation
13%
Feature Extraction
13%
Simple Moving Average
13%
Feature Information
13%
Simplicial Cone
13%
Equal Error Rate
13%
Single System
13%
Quantized Input
11%
Model Compression
11%
Edge Contour
10%
Visual Geometry Group
10%
Binary Hashing
10%
Network Depth
10%
Deep CNN Models
10%
Fracture Location
10%
Neural Network Architecture
10%
Analysis Filter
10%
Lack of Consensus
10%
Sagittal
10%
Area Matching
10%
Difficult-to-treat
10%
Human-based
10%
Feature Algorithm
10%
Augmentor
10%
Bone Fracture Classification
10%
RESIDE
10%
Dehazing
10%
Pyramid Module
10%
Spatial Pyramid
10%
Computer-aided System
10%
Artificial Images
10%
Rotation Distortion
10%
Differential Training
10%
Augmented Training
10%
Background Classification
10%
Performance Accuracy
10%
Visual Geometry Group Network
10%
Deep Learning Network
10%
Deep Learning Neural Network
10%
Bone Fracture Detection
10%
Tarsal Bones
10%
Anatomical Complexity
10%
Haze-free Image
10%
Atmospheric Scattering Model
10%
Encoded Features
10%
Contextual Level
10%
Stationery
10%
Network Performance
10%
Classification System
10%
Bone Fracture
10%
Low SNR
10%
Detection Algorithm
10%
Noise Problem
10%
Classification Results
10%
Histogram
10%
Convolutional Neural Network Architecture
10%
Feature-based
10%
Dataset Size
10%
Superior Performance
10%
Audio-only
10%
Training Approaches
10%
Deep Learning Algorithm
10%
Deep Learning Architectures
10%
Classification Accuracy
10%
Computer Science
Convolutional Neural Network
100%
Neural Network
86%
Experimental Result
86%
nonnegative matrix factorization
80%
Extreme Learning Machine
80%
Speech Enhancement
80%
Deep Learning Model
60%
Speech Emotion Recognition
40%
Deep Q-Network
40%
Data Representation
40%
Tracking State
40%
Speaker Characterization
40%
Long Short-Term Memory Neural Network
40%
Event Detection
40%
Image Dehazing
40%
Speech Recognition
40%
Pyramid Pooling Modules
40%
Spatial Structure
40%
Leibler Divergence
40%
Speaker Recognition
40%
time-delay
40%
Age Recognition
40%
Gender Recognition
40%
Information Retrieval
40%
Training Data
29%
Recognition Result
24%
Chatbot
20%
Robot
20%
Long Short-Term Memory Network
20%
Chat
20%
Contextual Information
20%
Objective Function
20%
Learning Approach
20%
Dictionary Learning
20%
Discriminability
20%
Image Segmentation
20%
Semantic Image
20%
Medical Diagnosis
20%
Annotation
20%
Multimedia
20%
Computer Vision
20%
Deep Learning Method
20%
Visual Informations
16%
Simple Average
13%
Parallel Architectures
13%
Extracted Feature
13%
Sparse Representation
13%
Equal Error Rate
13%
Detection Accuracy
13%
Data Augmentation
13%
Feature Information
13%
Feature Extraction
13%
Model Compression
11%
Word Error Rate
8%
Tracking Method
8%
Speech Recognition System
8%
Deep Reinforcement Learning
8%
Noisy Environment
8%
Testing Condition
8%
Performance Enhancement
8%
Objective Measure
8%
Dialog System
8%
Facial Expression
6%
Sentiment Analysis
6%
Voice Assistant
6%
Deep Convolutional Neural Networks
5%
binarization
5%
Learning Process
5%
Representation Learning
5%
Computational Cost
5%
Achievable Performance
5%
World Application
5%
Evaluation Metric
5%
Compression Technique
5%