End-to-End Speech Recognition Sequence Training With Reinforcement Learning.
Andros TjandraSakriani SaktiSatoshi NakamuraPublished in: IEEE Access (2019)
Keyphrases
- end to end
- speech recognition
- reinforcement learning
- wall street journal corpus
- isolated word
- hidden markov models
- language model
- acoustic models
- speech signal
- automatic speech recognition
- pattern recognition
- speech recognizer
- speech processing
- speech recognition technology
- speech synthesis
- speech recognition systems
- congestion control
- noisy environments
- machine learning
- speaker independent
- information retrieval
- discriminative training
- speaker identification
- speech retrieval
- speech recognizers
- audio visual speech recognition