Keyphrases
Speech Recognition
85%
Hidden Markov Model
65%
Adaptation
38%
Language Modeling
31%
Language Model
30%
Sequential Learning
24%
Variational
24%
Bayesian Learning
23%
End-to-end Speech Recognition
23%
Recurrent Neural Network
20%
I-vector
18%
Neural Network
17%
International Cooperative Ataxia Rating Scale (ICARS)
16%
Hyperparameters
16%
Non-negative Matrix Factorization
16%
Speaker Adaptation
16%
Maximum a Posteriori
16%
Domain Adaptation
15%
Deep Neural Network
15%
Speaker Recognition
14%
Acoustic Modeling
14%
Speech Separation
14%
Target Domain
13%
Latent Dirichlet Allocation
13%
Speaker Verification
13%
Source Separation
12%
Dialogue Policy
12%
Natural Language Understanding
12%
Variational Autoencoder
11%
N-gram
11%
Sequence Data
11%
Latent Topics
11%
Linear Regression
11%
Variational Inference
11%
Transformer
11%
Latent Variable Models
11%
Telephone Speech
11%
Adversarial Learning
10%
Dialogue Systems
10%
Temporal Convolutional Network
10%
Decoder
10%
Large Vocabulary Continuous Speech Recognition (LVCSR)
10%
Natural Language
9%
Posterior Collapse
9%
Source Domain
9%
Encoder
9%
Long Short-term Memory
9%
Speech Signal
9%
Soft Prompt
9%
Factor Analysis
9%
Computer Science
Speech Recognition
100%
Language Modeling
60%
Neural Network
39%
Recurrent Neural Network
27%
Bayesian Learning
27%
Sequential Learning
26%
Experimental Result
24%
Speaker Verification
18%
Adaptation Data
18%
Regularization
18%
Source Separation
18%
Dialog System
17%
Reinforcement Learning
17%
Leaning Parameter
17%
nonnegative matrix factorization
16%
Latent Dirichlet Allocation
16%
maximum-likelihood
15%
Domain Adaptation
14%
Machine Learning
14%
Autoencoder
14%
Speaker Recognition
14%
Independent Component Analysis
13%
Training Data
13%
Attention (Machine Learning)
13%
Contrastive Learning
13%
Mutual Information
12%
Feature Extraction
12%
Latent Variable Model
12%
Deep Neural Network
12%
Linear Discriminant Analysis
11%
Learning System
11%
Natural-Language Understanding
11%
Long Short-Term Memory Network
10%
Seq2Seq
10%
Variational Autoencoder
10%
Meta-Learning
10%
Transformation Parameter
9%
And-States
9%
Learning Algorithm
9%
Data Augmentation
9%
Blind Signal Separation
8%
Recognition Performance
8%
Pre-Trained Language Models
8%
Classification Accuracy
8%
Dirichlet Process
8%
Telephone
8%
Manifold Learning
7%
Sparse Learning
7%
Marginal Likelihood
7%
Semisupervised Learning
7%
Engineering
Recurrent Neural Network
25%
Model Parameter
25%
Reinforcement Learning
25%
Experimental Result
19%
Gaussians
19%
Maximum a Posteriori
18%
Source Separation
18%
Matrix Factorization
16%
Long Short-Term Memory
13%
Telephone
13%
Language Understanding
12%
Deep Neural Network
12%
Independent Component Analysis
11%
Regularization
11%
Learning System
11%
Robust Speech Recognition
10%
Basis Vector
10%
Speech Enhancement
10%
Dirichlet
10%
Autoencoder
9%
Maximum Likelihood
9%
Speech Signal
9%
Feature Extraction
8%
Deep Learning Method
8%
Single Channel
7%
Recurrent
7%
Systems Performance
7%
Conjugate Prior
7%
Latent Variable Model
7%
Posterior Probability
7%
Error Rate
7%
Recognizer
6%
Blind Signal Separation
6%
Signal-to-Noise Ratio
6%
Illustrates
6%
Bayesian Approach
6%
Source Signal
6%
Acoustic Feature
6%
Joints (Structural Components)
6%
Mutual Information
6%
Bayesian Model
6%
Model Uncertainty
5%
Continuous Speech Recognition
5%
Microphone Array
5%
Feature Vector
5%
Parameter Estimation
5%
Input Sequence
5%
Recursive
5%
Recognition Accuracy
5%
Hypothesis Test
5%