Lightly supervised acoustic model training for imprecisely and asynchronously transcribed speech.
Péter MihajlikAndrás BalogPublished in: SpeD (2013)
Keyphrases
- supervised learning
- spontaneous speech
- hearing impaired
- training examples
- training stage
- unsupervised learning
- speech recognition
- learning algorithm
- feature selection
- endpoint detection
- supervised training
- test set
- training set
- data sets
- back propagation
- training samples
- information retrieval
- training algorithm
- supervised classification
- automatic speech recognition
- semi supervised
- feature vectors
- machine learning
- neural network