Joint acoustic modeling of triphones and trigraphemes by multi-task learning deep neural networks for low-resource speech recognition.
Dongpeng ChenBrian MakCheung-Chi LeungSunil SivadasPublished in: ICASSP (2014)
Keyphrases
- speech recognition
- multi task learning
- speech recognition systems
- neural network
- pattern recognition
- speaker independent
- speech recognizers
- multi task
- language model
- hidden markov models
- speech signal
- learning tasks
- gaussian processes
- speech recognizer
- automatic speech recognition
- acoustic models
- speech synthesis
- speaker identification
- high order
- learning problems
- transfer learning
- learning models
- support vector machine
- image processing
- learning algorithm