Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition.
Zhifu GaoShiliang ZhangIan McLoughlinZhijie YanPublished in: INTERSPEECH (2022)
Keyphrases
- end to end
- speech recognition
- autoregressive
- non stationary
- hidden markov models
- language model
- speech signal
- pattern recognition
- random fields
- speech synthesis
- automatic speech recognition
- speech recognizer
- congestion control
- spectral analysis
- speech recognition systems
- sar images
- conditional random fields
- probabilistic model
- speaker identification
- image data
- high resolution
- video sequences
- image sequences