Shifted Chunk Encoder for Transformer Based Streaming End-to-End ASR. (arXiv:2203.15206v2 [cs.SD] UPDATED)

Web: http://arxiv.org/abs/2203.15206

Currently, there are mainly three Transformer encoder based streaming End to
End (E2E) Automatic Speech Recognition (ASR) approaches, namely time-restricted
methods, chunk-wise methods, and memory based methods. However, all of them
have some limitations in aspects of global context modeling, linear
computational complexity, and model parallelism. In this work, we aim to build
a single model to achieve the benefits of all the three aspects for streaming
E2E ASR. Particularly, we propose to use a shifted chunk mechanism instead of …

arxiv asr encoder streaming transformer