Improved low-resource Somali speech recognition by semi-supervised acoustic and language model training.
Astik BiswasRaghav MenonEwald van der WesthuizenThomas NieslerPublished in: CoRR (2019)
Keyphrases
- speech recognition
- language model
- acoustic models
- semi supervised
- speech recognition systems
- speaker independent
- speech recognizers
- language modeling
- speech recognizer
- automatic speech recognition
- n gram
- speech signal
- probabilistic model
- speech synthesis
- retrieval model
- document retrieval
- supervised learning
- query expansion
- information retrieval
- semi supervised learning
- speaker identification
- test collection
- mixture model
- word error rate
- query terms
- handwriting recognition
- pattern recognition
- machine learning
- out of vocabulary
- labeled data
- noisy environments
- relevance model
- co training
- unlabeled data
- active learning