Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition.
Zhengkun TianJiangyan YiJianhua TaoYe BaiShuai ZhangZhengqi WenPublished in: INTERSPEECH (2020)
Keyphrases
- end to end
- speech recognition
- autoregressive
- non stationary
- hidden markov models
- language model
- speech recognizer
- automatic speech recognition
- speech synthesis
- random fields
- pattern recognition
- speech signal
- spectral analysis
- sar images
- linear prediction
- speaker identification
- speech recognition systems
- image processing
- information retrieval
- maximum entropy
- image restoration
- image compression
- video sequences
- bayesian networks