Passer à la navigation principale
Passer à la recherche
Passer au contenu principal
Trier par
Keyphrases
Audio
75%
Adversarial Attack
59%
Spectrogram
55%
Graphics Processing Unit
55%
Speech Recognition System
53%
Emotion Recognition
50%
Audio-visual Fusion
44%
Content-based
44%
GAN
44%
Speech Recognition
42%
I-vector
40%
Nearest Neighbor
38%
Audio Copy Detection
37%
TRECVID
37%
Valence
35%
Cross-attention
35%
Detection System
33%
Parallel Architecture
33%
Textual Adversarial Attack
33%
Discrete Wavelet Transform
31%
Feature Representation
31%
Environmental Sounds
31%
Copy Detection
31%
Text-to-speech
30%
Deep Neural Network
29%
Fusion Model
29%
Vocal
29%
Deep Learning Model
29%
Detector Response
28%
Recognition Accuracy
27%
Closed Captions
27%
Black-box Adversarial Attack
27%
Dimensional Emotion Recognition
25%
Environmental Sound Classification
25%
Defense Approach
25%
Nonverbal
25%
Concordance Correlation Coefficient
24%
Transcription System
24%
Audio Signal
24%
Kaldi
23%
Attention Model
22%
Word Error Rate
22%
Correction Module
22%
Real-time Correction
22%
Speaker Recognition
22%
2D Representation
22%
Sobolev
22%
Audio Events
22%
Live TV Broadcasts
22%
Captioning System
22%
Computer Science
Adversarial Machine Learning
100%
Speech Recognition
75%
Speech Recognition System
54%
Graphics Processing Unit
53%
Experimental Result
49%
Convolutional Neural Network
42%
Text To Speech
40%
Attention (Machine Learning)
38%
Individual Modality
37%
Graphics Processor
33%
Parallel Architectures
33%
Recurrent Network
33%
Deep Learning Model
30%
Recognition Accuracy
30%
Deep Neural Network
29%
Wavelet Transform
25%
Facial Expression
24%
Speech Recognizer
22%
Residual Neural Network
22%
Optimal Threshold
22%
segmentation accuracy
22%
Fusion Technique
22%
Visual Feature
22%
Behavior Analysis
22%
Speaker Recognition
22%
Parallelization
20%
Mel-Frequency Cepstral Coefficients
19%
Long Short-Term Memory Network
19%
Supervised Learning
18%
Modern Processor
18%
Generator Network
18%
Speed-up
17%
Word Error Rate
16%
Amplitude Modulation
16%
Support Vector Machine
16%
Noisy Environment
16%
Domain Adaptation
16%
Moore's Law
14%
Generative Adversarial Networks
14%
Parallel Processing
14%
Discriminator
14%
Weakly Supervised Domain Adaptation
14%
Gaussian Mixture Model
13%
Intensity Level
13%
World Application
13%
Language Identification
12%
Named Entity Recognition
11%
Detection Algorithm
11%
Convolutional Layer
11%
Quotation Mark
11%
