SSCFormer: Push the Limit of Chunk-wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolution

Currently, the chunk-wise schemes are often used to make Automatic Speech Recognition (ASR) models to support streaming deployment. However, existing approaches are unable to capture the global context, lack support for parallel training, or exhibit quadratic complexity for the computation of multi-head self-attention (MHSA). On the other side, the causal convolution, no future context used, has become the de facto module in streaming Conformer. In this paper, we propose SSCFormer to push the limit of chunk-wise Conformer for streaming ASR …

asr automatic speech recognition complexity computation context convolution cs.cl cs.sd deployment eess.as global head multi-head recognition speech speech recognition streaming support training wise