Keyphrases
Acoustic Modeling
28%
Adaptation
38%
Adaptive Algorithm
13%
Automatic Speech Recognition
16%
Cepstral Domain
16%
Channel Adaptation
16%
Continuous Density
20%
Conversion Method
14%
Deep Neural Network
39%
End-to-end Speech Recognition
38%
Environmental Noise
13%
Error Rate
17%
Fast Adaptation
12%
Fast Channel
16%
Gaussian Mixture Model
12%
Hidden Markov Model
100%
Many-to-many
19%
Maximum Likelihood
61%
Maximum Likelihood Linear Regression
13%
Mobile Environment
17%
Model Adaptation
15%
Neural Network
52%
Parallel Training
18%
Phase Transformation
20%
Pipeline Parallelism
11%
Rapid Adaptation
14%
Recognizer
21%
Robust Voice Activity Detection
16%
Sound Source Localization
25%
Speaker Anonymization
17%
Speaker Identification
17%
Spectral Domain
32%
Spectral Peak
14%
Spectral Transform
12%
Spectral Transformation
37%
Speech Data
17%
Speech Recognition
38%
Speech Recognition System
17%
Speech Recognizer
47%
Steered Response Power
20%
Stochastic Gradient Algorithm
14%
Stochastic Gradient Descent
15%
Training Algorithm
20%
Training Data
18%
Triphone
12%
Unknown Environment
23%
Viseme
16%
Voice Activity Detection
19%
Voice Conversion
48%
Voice User Interface
17%
Computer Science
Adaptation Data
22%
Anonymization
24%
Autoencoder
16%
cepstral
15%
Context Dependent
8%
Conventional Method
12%
Deep Neural Network
40%
Experimental Result
23%
Friendly Interface
8%
Gaussian Mixture Model
17%
Generative Adversarial Networks
12%
Gradient Descent
24%
Identity Information
8%
localization algorithm
10%
maximum-likelihood
59%
Mobile Environment
14%
Model Adaptation
12%
Mutual Information
16%
Neural Network
32%
Noise-to-Signal Ratio
9%
Noisy Environment
12%
Objective Function
11%
Parameter Estimation
9%
Pipeline Parallelism
11%
Recognition Accuracy
14%
Recognition System
13%
Recognizer
32%
Right Context
8%
Robust Speech Recognition
24%
Search Space
10%
Source Localization
25%
Speaker Identification
20%
Speaker Recognition
16%
Spectral Domain
16%
Spectral Transform
14%
Speech Adaptation
8%
speech corpus
20%
Speech Recognition
54%
Speech Recognition System
18%
Speech Recognizer
37%
Speed-up
9%
Table Lookup
8%
Taylor Expansion
8%
Telephone
9%
Testing Condition
9%
Text Classification
8%
training algorithm
20%
Training Data
22%
Tree-Based Clustering
8%
Voice Activity Detection
18%
Engineering
Adaptation Models
20%
Audio Signal
16%
Automatic Speech Recognition
22%
Classification Method
8%
Closed Form Solution
8%
Compensation Network
10%
Continuous Speech Recognition
8%
Daily Life
8%
Decoding Procedure
8%
Deep Neural Network
24%
Detection Algorithm
8%
Environmental Noise
10%
Error Rate
33%
Experimental Result
11%
Feature Transform
8%
Feature Vector
15%
Gaussian Mixture Model
9%
Home Environment
8%
Hybrid Model
8%
Input Signal
10%
Lookup Table
8%
Matched Filter
8%
Maximum Likelihood
71%
Medical Image
8%
Microphone Array
15%
Mutual Information
8%
Noisy Environment
8%
Objective Function
20%
Operating Environment
8%
Output Sequence
8%
Performance Degradation
10%
Probability Density Function
8%
Recognition Accuracy
19%
Recognizer
65%
Reverberation
12%
Robot
8%
Robust Speech Recognition
35%
Search Algorithm
8%
Search Space
9%
Signal-to-Noise Ratio
18%
Sound Source
24%
Speaker Identification
8%
Speaker Recognition System
8%
Spectral Characteristic
8%
Spectral Domain
24%
Spectral Transform
10%
Taylor Series
8%
Telephone
15%
Test Signal
8%
Testing Condition
11%
