Leveraging Multi-Task Learning with Neural Network Based Acoustic Modeling for Improved Meeting Speech Recognition.
Ming-Han YangYao-Chi HsuHsiao-Tsung HungYing-Wen ChenKuan-Yu ChenBerlin ChenPublished in: Int. J. Comput. Linguistics Chin. Lang. Process. (2016)
Keyphrases
- speech recognition
- multi task learning
- speech recognition systems
- multi task
- speaker independent
- speech recognizers
- hidden markov models
- speaker diarization
- acoustic models
- language model
- automatic speech recognition
- learning tasks
- speech recognizer
- gaussian processes
- neural network
- speech synthesis
- pattern recognition
- speech signal
- high order
- speaker identification
- noisy environments
- learning problems
- probabilistic model
- transfer learning
- learning models
- learning algorithm
- text classification
- inductive learning