Engineering & Materials Science
Acoustic waves
46%
Acoustics
29%
Anthropomorphic robots
18%
Beamforming
10%
Blind source separation
17%
Cameras
6%
Chemical activation
5%
Classifiers
14%
Communication
11%
Condition monitoring
6%
Continuous speech recognition
28%
Convolutional neural networks
13%
Costs
5%
Crowdsourcing
11%
Deep neural networks
19%
Degradation
5%
Detectors
5%
Direction of arrival
7%
Discriminant analysis
10%
Entropy
7%
Experiments
24%
Feature extraction
14%
Feedback
7%
Fish
10%
Gesture recognition
20%
Hidden Markov models
31%
Image classification
8%
Independent component analysis
7%
Labels
5%
Linear programming
6%
Linguistics
27%
Machine learning
10%
Masks
10%
Microphones
44%
Mobile computing
8%
Mobile robots
8%
Neural networks
8%
Noise abatement
6%
Nonlinear distortion
7%
Object detection
13%
Pattern recognition
6%
Recurrent neural networks
14%
Robots
59%
Semantics
21%
Source separation
24%
Speech enhancement
25%
Speech recognition
100%
Speech synthesis
24%
Syntactics
7%
Wind turbines
5%
Arts & Humanities
Acoustics
18%
Continuous Speech
33%
Conventional
8%
Data Base
6%
Dialogue Acts
5%
Dialogue Systems
6%
Dictation
8%
Dirichlet
10%
Entropy
7%
Evaluation
5%
Experiment
5%
Feature Selection
5%
Filled Pause
6%
Filter
8%
Hidden Markov Model (HMM)
10%
Mixture Model
8%
Module
5%
Mutual Information
17%
N-gram
6%
News
8%
Phoneme
17%
Phonemics
12%
Prediction
8%
Proficiency
8%
Prosody
11%
Repository
7%
Robot
14%
Sentence-final Particles
5%
Software
6%
Sound
9%
Speech Recognition
80%
Speech Synthesis
16%
Spoken Dialogue Systems
27%
Subtraction
5%
Telephone
5%
Turn-taking
6%
Vocabulary
20%
Waves
5%
Mathematics
Acoustics
8%
Automatic Speech Recognition
6%
Contour Extraction
6%
Corpus
6%
Data Sharing
5%
Dialogue
14%
Dirichlet Process
8%
Encoder
5%
Engagement
5%
Experiment
10%
Fault Detection
5%
Framework
7%
Human
5%
Language Model
8%
Learning
6%
Model
6%
Model-based
5%
Neural Networks
8%
Prosody
9%
Robot
18%
Source Separation
10%
Speaker Verification
6%
Spectrality
5%
Speech
35%
Speech Enhancement
12%
Speech Recognition
27%
Speech Synthesis
5%
Spoken Dialogue Systems
16%
Target
6%
Text
8%
Timing
7%
Training
11%
Voice
5%
