Keyphrases
Adversarial Attack
77%
Attack Algorithm
22%
Attention Model
22%
Audio
75%
Audio Copy Detection
36%
Audio Events
22%
Audio Signal
24%
Audio-visual Fusion
44%
Closed Caption
25%
Concordance Correlation Coefficient
24%
Content-based
44%
Copy Detection
31%
Correction Module
22%
Cross-attention
35%
Cycle-consistent Adversarial Network
22%
Deep Learning Model
26%
Deep Neural Network
29%
DeepSpeech
24%
Defense Algorithm
26%
Defense Approaches
32%
Detection System
33%
Detection Task
27%
Dimensional Emotion Recognition
25%
Discrete Wavelet Transform
31%
Emotion Recognition
50%
Environmental Sound Classification
25%
Environmental Sounds
29%
Feature Representation
44%
Fusion Model
29%
Graphics Processing Unit
55%
I-vector
40%
Input Signals
22%
Kaldi
30%
Nearest Neighbor
38%
Nonverbal
25%
Parallel Architecture
33%
Real-time Correction
22%
Recognition Accuracy
27%
Sobolev
22%
Spectrogram
61%
Speech Recognition
40%
Speech Recognition System
53%
Speech-to-text
41%
Targeted Adversarial Attack
22%
Transcription System
27%
TRECVID
37%
Valence
35%
Vocal
29%
White-box
24%
Word Error Rate
22%
Computer Science
Adversarial Machine Learning
100%
Amplitude Modulation
16%
Attention (Machine Learning)
33%
Automated Operation
11%
Benchmarking
15%
Broadcast News
15%
Convolutional Layer
11%
Convolutional Neural Network
42%
Deep Learning Model
17%
Deep Neural Network
33%
Detection Algorithm
11%
Discriminator
14%
Domain Adaptation
16%
Experimental Result
49%
Facial Expression
20%
Fusion Technique
16%
Gaussian Mixture Model
13%
Generative Adversarial Networks
14%
Generator Network
18%
Graphics Processing Unit
53%
Graphics Processor
33%
Individual Modality
31%
Intensity Level
13%
Language Identification
12%
Long Short-Term Memory Network
19%
Mel-Frequency Cepstral Coefficients
19%
Modern Processor
18%
Moore's Law
14%
Named Entity Recognition
11%
Noisy Environment
16%
Optimal Threshold
22%
Parallel Architectures
33%
Parallel Processing
14%
Parallelization
20%
Quotation Mark
11%
Recognition Accuracy
30%
Recurrent Network
27%
Residual Neural Network
22%
segmentation accuracy
22%
Speech Recognition
78%
Speech Recognition System
54%
Speech Recognizer
22%
Speed-up
17%
Support Vector Machine
16%
Text To Speech
40%
Visual Feature
16%
Visual Modality
22%
Wavelet Transform
25%
Weakly Supervised Domain Adaptation
14%
Word Error Rate
27%
