Streaming Attention-Based Models with Augmented Memory for End-To-End Speech Recognition.
Ching-Feng YehYongqiang WangYangyang ShiChunyang WuFrank ZhangJulian ChanMichael L. SeltzerPublished in: SLT (2021)
Keyphrases
- end to end
- speech recognition
- language model
- scalable video
- hidden markov models
- speech processing
- acoustic models
- speech signal
- speech recognizer
- automatic speech recognition
- congestion control
- probabilistic model
- machine learning
- speech synthesis
- content delivery
- noisy environments
- speech recognition technology
- pattern recognition
- speech recognition systems
- speaker independent
- speaker dependent
- isolated word
- speaker identification
- non stationary
- wavelet transform
- image processing