Transformer-based end-to-end speech recognition with residual Gaussian-based self-attention.
Chengdong LiangMenglong XuXiao-Lei ZhangPublished in: CoRR (2021)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- language model
- speech synthesis
- automatic speech recognition
- speech recognizer
- speech processing
- speech signal
- noisy environments
- pattern recognition
- congestion control
- speaker identification
- maximum likelihood
- speech recognition systems
- speech recognition technology
- gaussian mixture model
- edge detection
- speaker independent
- scalable video
- image compression
- speech recognizers
- isolated word