Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition.
Zhengkun TianJiangyan YiJianhua TaoYe BaiShuai ZhangZhengqi WenPublished in: CoRR (2020)
Keyphrases
- end to end
- autoregressive
- speech recognition
- non stationary
- hidden markov models
- speech synthesis
- language model
- random fields
- automatic speech recognition
- pattern recognition
- speech recognizer
- speech signal
- speaker identification
- spectral analysis
- speech recognition systems
- linear prediction
- sar images
- multiresolution
- information retrieval
- generative model
- image compression
- mobile devices
- multiscale