Improving End-to-end Speech Recognition with Pronunciation-assisted Sub-word Modeling.
Hainan XuShuoyang DingShinji WatanabePublished in: ICASSP (2019)
Keyphrases
- speech recognition
- end to end
- speech recognizer
- speech recognition systems
- wall street journal corpus
- keyword spotting
- hidden markov models
- speech recognizers
- automatic speech recognition
- speech processing
- word error rate
- language model
- speech synthesis
- speaker independent
- speech signal
- congestion control
- speech recognition technology
- pattern recognition
- speaker identification
- acoustic models
- handwriting recognition
- noisy environments
- n gram
- word recognition
- image processing
- machine learning
- speaker adaptation
- feature vectors
- computer vision