Engineering & Materials Science
Speech recognition
100%
Robots
60%
Acoustic waves
46%
Microphones
45%
Hidden Markov models
31%
Acoustics
29%
Continuous speech recognition
28%
Linguistics
26%
Speech enhancement
26%
Experiments
24%
Speech synthesis
24%
Source separation
24%
Semantics
21%
Gesture recognition
20%
Deep neural networks
19%
Anthropomorphic robots
18%
Blind source separation
17%
Feature extraction
15%
Classifiers
14%
Recurrent neural networks
14%
Convolutional neural networks
13%
Object detection
13%
Communication
11%
Fish
10%
Beamforming
10%
Discriminant analysis
10%
Masks
10%
Machine learning
10%
Neural networks
9%
Image classification
8%
Mobile computing
8%
Mobile robots
8%
Independent component analysis
7%
Crowdsourcing
7%
Nonlinear distortion
7%
Feedback
7%
Entropy
7%
Direction of arrival
7%
Condition monitoring
6%
Pattern recognition
6%
Noise abatement
6%
Cameras
6%
Linear programming
6%
Detectors
5%
Chemical activation
5%
Degradation
5%
Wind turbines
5%
Probability density function
5%
Costs
5%
Acoustic intensity
5%
Arts & Humanities
Speech Recognition
79%
Continuous Speech
33%
Spoken Dialogue Systems
21%
Vocabulary
20%
Acoustics
18%
Phoneme
18%
Mutual Information
17%
Speech Synthesis
16%
Robot
15%
Phonemics
13%
Prosody
11%
Dirichlet
10%
Hidden Markov Model (HMM)
10%
Sound
9%
News
8%
Filter
8%
Mixture Model
8%
Proficiency
8%
Dictation
8%
Entropy
7%
Repository
7%
Filled Pause
6%
Conventional
6%
Software
6%
N-gram
6%
Dialogue Systems
6%
Turn-taking
6%
Data Base
6%
Evaluation
6%
Prediction
5%
Experiment
5%
Telephone
5%
Feature Selection
5%
Subtraction
5%
Dialogue Acts
5%
Waves
5%
Sentence-final Particles
5%
Module
5%
Mathematics
Speech
35%
Speech Recognition
27%
Robot
18%
Spoken Dialogue Systems
17%
Dialogue
14%
Speech Enhancement
12%
Source Separation
10%
Experiment
10%
Training
10%
Prosody
9%
Acoustics
9%
Text
8%
Neural Networks
8%
Language Model
8%
Dirichlet Process
8%
Timing
7%
Corpus
6%
Framework
6%
Speaker Verification
6%
Contour Extraction
6%
Target
6%
Model
6%
Automatic Speech Recognition
6%
Data Sharing
6%
Speech Synthesis
6%
Learning
5%
Model-based
5%
Voice
5%
Human
5%
Encoder
5%
Spectrality
5%
Fault Detection
5%
Engagement
5%
Linguistics
5%