Multilingual Training Set Selection for ASR in Under-Resourced Malian Languages.
Ewald van der WesthuizenTrideba PadhiThomas NieslerPublished in: SPECOM (2021)
Keyphrases
- training set
- language independent
- cross lingual
- multi lingual
- multilingual information retrieval
- data sets
- multilingual documents
- training data
- language resources
- language specific
- nearest neighbor
- automatic speech recognition
- classification accuracy
- test set
- expressive power
- speech recognition
- test data
- cross lingual information retrieval
- training examples
- supervised learning
- cross validation
- svm classifier
- bilingual dictionaries
- databases
- decision trees
- digital libraries
- feature space
- indian languages
- active learning
- parallel corpus
- hidden markov models
- training samples
- language identification
- statistical machine translation
- face images
- information retrieval systems
- text classification
- test images
- machine translation