Semi-supervised acoustic model training for five-lingual code-switched ASR.
Astik BiswasEmre YilmazFebe de WetEwald van der WesthuizenThomas NieslerPublished in: CoRR (2019)
Keyphrases
- semi supervised
- supervised learning
- fully labeled
- semi supervised learning
- training process
- multi view
- source code
- online learning
- speech recognition
- labeled data
- data sets
- training set
- training algorithm
- automatic speech recognition
- neural network
- open source
- batch mode
- computer software
- co training
- test set
- unlabeled data
- unsupervised learning