ASKCC-DCNN-CTC: A Multi-Core Two Dimensional Causal Convolution Fusion Network with Attention Mechanism for End-to-End Speech Recognition.
Rongchuang LvNiansheng ChenSonglin ChengGuangyu FanLei RaoXiaoyong SongDingyu YangPublished in: CSCWD (2023)
Keyphrases
- end to end
- speech recognition
- congestion control
- internet protocol
- hidden markov models
- attention mechanism
- speech synthesis
- speech signal
- transport layer
- language model
- pattern recognition
- speech recognizer
- speech recognition systems
- automatic speech recognition
- differentiated services
- bayesian networks
- transport protocol
- speaker identification
- video sequences
- network layer
- visual attention
- visual features
- mobile devices