Exploring Pre-training with Alignments for RNN Transducer based End-to-End Speech Recognition.
Hu HuRui ZhaoJinyu LiLiang LuYifan GongPublished in: CoRR (2020)
Keyphrases
- end to end
- speech recognition
- wall street journal corpus
- isolated word
- hidden markov models
- acoustic models
- pattern recognition
- recurrent neural networks
- language model
- speech recognizer
- automatic speech recognition
- speech processing
- speech synthesis
- noisy environments
- speech recognition systems
- congestion control
- speech signal
- speaker independent
- speech recognition technology
- training set
- speaker identification
- speech retrieval
- neural network
- mobile devices
- speaker adaptation
- computer vision
- machine learning