Improving RNN Transducer Modeling for End-to-End Speech Recognition.
Jinyu LiRui ZhaoHu HuYifan GongPublished in: CoRR (2019)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- speech processing
- automatic speech recognition
- language model
- speech signal
- congestion control
- pattern recognition
- speech recognizer
- speech synthesis
- speech recognition systems
- noisy environments
- speech recognition technology
- recurrent neural networks
- speaker identification
- speech retrieval
- background noise
- isolated word
- speech recognizers
- computer vision
- acoustic models
- bayesian networks