Improved Low-Resource Somali Speech Recognition by Semi-Supervised Acoustic and Language Model Training.
Astik BiswasRaghav MenonEwald van der WesthuizenThomas NieslerPublished in: INTERSPEECH (2019)
Keyphrases
- speech recognition
- language model
- acoustic models
- semi supervised
- speech recognition systems
- language modeling
- speech recognizers
- speaker independent
- speech recognizer
- document retrieval
- automatic speech recognition
- supervised learning
- n gram
- probabilistic model
- information retrieval
- speech synthesis
- query expansion
- semi supervised learning
- handwriting recognition
- speech signal
- retrieval model
- test collection
- mixture model
- word error rate
- unlabeled data
- labeled data
- neural network
- statistical machine translation
- query terms
- translation model
- noisy environments
- training set
- unsupervised learning
- active learning
- hidden markov models
- speaker identification
- feature vectors
- natural language processing
- machine learning