Improving RNN Transducer Modeling for End-to-End Speech Recognition.
Jinyu LiRui ZhaoHu HuYifan GongPublished in: ASRU (2019)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- speech recognizer
- speech synthesis
- language model
- speech signal
- automatic speech recognition
- noisy environments
- speech processing
- speech recognition systems
- recurrent neural networks
- speech recognition technology
- speaker identification
- pattern recognition
- congestion control
- speech recognizers
- isolated word
- text localization and recognition
- speaker independent
- speaker dependent
- speech retrieval
- image processing
- feature selection
- information retrieval