Computer Science
Text To Speech
100%
Language Resource
66%
Transfer Learning
60%
Source Language
46%
Speech Synthesis
40%
Meta-Learning
40%
Feature Mapping
20%
Target Language
20%
Speech Synthesis System
20%
Language Family
16%
Phonological Feature
11%
Prediction Model
10%
Data Access
10%
Open Access
10%
Objective Measure
10%
Sufficient Data
10%
Systems Performance
10%
Representation Language
10%
Evaluation Metric
6%
Model Architecture
6%
Distance Measure
6%
Speech Recognition
6%
Language Specific
6%
Recognizer
5%
Training Data
5%
Keyphrases
Text-to-speech Synthesis
40%
Speech Synthesis
30%
Phonology
20%
Multilingual Data
20%
Phonetics
20%
Language Technology
20%
Pronunciation Dictionary
20%
MOS Prediction
20%
Mapping Language
20%
Fine-tuning Strategy
20%
Language Selection
20%
Phone Mapping
20%
Low-resource Speech Synthesis
20%
Text-to-speech Synthesis System
20%
Meta-learning
20%
Phoneme Frequencies
15%
Angular Similarity
15%
Challenging Tasks
10%
Zero-shot
10%
Language Representation
10%
Measurement Evaluation
10%
Linguistic Resources
10%
System Performance
10%
Speech Technology
10%
Linguistic Landscape
10%
Human Evaluation
10%
Balance Ratio
6%
Multilingual Text-to-speech
6%
Family Classification
6%
Neural TTS
6%
Shot Prediction
6%
Language Independence
6%
Phone Recognizer
5%
Cross-lingual Text-to-speech
5%
Pre-trained Acoustic Representations
5%
Phoneme System
5%
Social Sciences
Learning Transfer
40%
Text-to-Speech
40%
Systematic Review
20%
Phoneme
20%
Language Family
11%
Finnish Language
6%
Bulgarian Language
6%
Swahili
6%
Russian Language
6%
Uzbek
6%
Individual Languages
6%
Speech Recognition
6%
Kazakh
6%
