Adversarial joint training with self-attention mechanism for robust end-to-end speech recognition.
Lujun LiYikai KangYuchen ShiLudwig KürzingerTobias WatzelGerhard RigollPublished in: EURASIP J. Audio Speech Music. Process. (2021)
Keyphrases
- end to end
- speech recognition
- noisy environments
- language model
- isolated word
- attention mechanism
- hidden markov models
- speech synthesis
- automatic speech recognition
- acoustic models
- speech signal
- pattern recognition
- speech recognition systems
- text localization and recognition
- speech recognition technology
- speaker identification
- congestion control
- speaker independent
- speech recognizer
- visual attention
- bayesian networks