Stream attention-based multi-array end-to-end speech recognition.
Xiaofei WangRuizhi LiSri Harish MallidiTakaaki HoriShinji WatanabeHynek HermanskyPublished in: CoRR (2018)
Keyphrases
- end to end
- speech recognition
- language model
- automatic speech recognition
- speech processing
- hidden markov models
- speech recognition technology
- data streams
- speech synthesis
- pattern recognition
- speech recognizer
- speaker identification
- speech recognition systems
- speech signal
- congestion control
- sliding window
- noisy environments
- speech recognizers
- speaker dependent
- speech retrieval
- text localization and recognition
- isolated word
- multimedia
- multipath
- signal processing
- feature extraction