Advances in Joint CTC-Attention Based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM.
Takaaki HoriShinji WatanabeYu ZhangWilliam ChanPublished in: INTERSPEECH (2017)
Keyphrases
- end to end
- speech recognition
- language model
- language modeling
- hidden markov models
- automatic speech recognition
- speech recognizer
- speech synthesis
- rate allocation
- speech signal
- pattern recognition
- n gram
- information retrieval
- bit rate
- scalable video
- rate distortion
- congestion control
- speaker independent
- low complexity
- machine learning
- probabilistic model
- speaker dependent