To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition.
Yossi AdiNeil ZeghidourRonan CollobertNicolas UsunierVitaliy LiptchinskyGabriel SynnaevePublished in: CoRR (2018)
Keyphrases
- speech recognition
- multi task learning
- multi task
- multiple tasks
- gaussian processes
- learning tasks
- hidden markov models
- speech signal
- language model
- theoretical analysis
- learning problems
- automatic speech recognition
- speech synthesis
- high order
- edge detection
- transfer learning
- pattern recognition
- speech recognition systems
- speech recognizer
- learning algorithm
- inductive learning
- learning models
- supervised learning
- feature space
- bayesian networks
- computer vision