Orthogonal Gradient Penalty for Fast Training of Wasserstein GAN Based Multi-Task Autoencoder toward Robust Speech Recognition.
Chao-Yuan KaoSangwook ParkAlzahra BadiDavid K. HanHanseok KoPublished in: IEICE Trans. Inf. Syst. (2020)
Keyphrases
- speech recognition
- multi task
- noisy environments
- multi task learning
- hidden markov models
- isolated word
- speech signal
- automatic speech recognition
- acoustic models
- pattern recognition
- speaker identification
- speech synthesis
- learning tasks
- speech recognizer
- multi class
- language model
- learning problems
- training set
- feature selection
- transfer learning
- unsupervised learning
- edge detection
- speech recognition systems
- computer vision
- machine learning
- data mining
- training process
- e learning
- text categorization
- support vector machine
- active learning
- pairwise