Training Augmentation with Adversarial Examples for Robust Speech Recognition.
Sining SunChing-Feng YehMari OstendorfMei-Yuh HwangLei XiePublished in: CoRR (2018)
Keyphrases
- speech recognition
- noisy environments
- wall street journal corpus
- hidden markov models
- isolated word
- speech recognizer
- speech processing
- language model
- speech synthesis
- speech understanding
- pattern recognition
- speech recognition technology
- automatic speech recognition
- speech signal
- acoustic models
- speech recognition systems
- speaker independent
- speaker identification
- speech recognizers
- speech retrieval
- training set
- speaker dependent
- speech recognition errors
- training process
- neural network
- speaker diarization
- discriminative training
- data mining