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: CoRR (2017)
Keyphrases
- end to end
- speech recognition
- language model
- hidden markov models
- language modeling
- rate allocation
- speech signal
- speech recognition technology
- automatic speech recognition
- pattern recognition
- speech synthesis
- speech recognition systems
- probabilistic model
- noisy environments
- congestion control
- n gram
- bit rate
- speech recognizer
- speaker identification
- information retrieval
- speaker independent
- scalable video
- video codec
- low complexity
- video streams
- rate distortion