Unsupervised Pre-Training for Data-Efficient Text-to-Speech on Low Resource Languages.
Seongyeon ParkMyungseo SongBohyung KimTae-Hyun OhPublished in: ICASSP (2023)
Keyphrases
- data sets
- data analysis
- raw data
- database
- text to speech
- training data
- data collection
- data structure
- training examples
- labelled data
- resource allocation
- training samples
- small number
- knowledge discovery
- xml documents
- neural network
- image data
- supervised learning
- data processing
- data model
- high dimensional
- data mining
- databases