Computer Science
Speech Synthesis
100%
Speech Recognition
73%
Text To Speech
59%
Synthetic Speech
34%
Deep Neural Network
30%
Neural Network
21%
Language Modeling
21%
Acoustic Feature
19%
Word Error Rate
19%
Training Data
18%
Speech Synthesis System
18%
Speech Recognition System
17%
Speaker Verification
16%
Recurrent Neural Network
14%
Subjective Evaluation
13%
Annotation
12%
Spoofing
11%
Broadcast News
10%
Spoken Language
10%
Experimental Result
10%
Speech Synthesizer
8%
Seq2Seq
7%
speech corpus
7%
Gaussian Mixture Model
7%
Context Dependent
7%
Machine Translation
7%
Dynamic Bayesian Network
6%
Speech Waveform
6%
Evaluation Result
6%
Information Retrieval
6%
Target Language
5%
Dialog System
5%
Model Adaptation
5%
Feature Extraction
5%
maximum-likelihood
5%
Multitask Learning
5%
Support Vector Machine
5%
Expressive Speech
5%
Engineering
Deep Neural Network
29%
Acoustic Feature
19%
Automatic Speech Recognition
16%
Error Rate
14%
Recurrent Neural Network
12%
Speech Waveform
11%
Speech Signal
10%
Subjective Evaluation
8%
Speech Data
8%
Joints (Structural Components)
7%
Gaussian Mixture Model
7%
Experimental Result
6%
Summarization
5%
Phase Spectrum
5%
Harmonics
5%
Feature Extraction
5%
Arts and Humanities
Speech Synthesis
17%
Speaker
13%
Corpus
10%
Dialogue Form
8%
Speech Recognition
8%
Utterance
7%
Automatic Speech Recognition
6%
Linguistics
6%
Prosody
5%