Language diarization for semi-supervised bilingual acoustic model training.
Emre YilmazMitchell McLarenHenk van den HeuvelDavid A. van LeeuwenPublished in: ASRU (2017)
Keyphrases
- semi supervised
- supervised learning
- fully labeled
- parallel corpus
- machine translation
- target language
- semi supervised learning
- unlabeled data
- language resources
- training process
- labeled data
- natural language
- training set
- bilingual dictionaries
- training examples
- word alignment
- programming language
- language learning
- semi supervised classification
- source language
- semi supervised clustering
- indian languages
- comparable corpora
- labeled examples
- co training
- training data
- training samples