SSCFormer: Push the Limit of Chunk-Wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolution.
Fangyuan WangBo XuBo XuPublished in: IEEE Signal Process. Lett. (2024)
Keyphrases
- data streams
- speech recognition
- image processing
- video streaming
- pairwise
- real time
- automatic speech recognition
- bayesian networks
- data streaming
- streaming data
- causal models
- neural network
- spoken words
- linear filtering
- directed acyclic graph
- noisy environments
- causal reasoning
- causal relations
- causal networks
- concept drift
- causal independence
- causal knowledge
- peer to peer
- convolution kernel
- real time streaming
- speech retrieval
- data sets