Shengqiang Li — accepted AI-conference papers

2023

Fast-U2++: Fast and Accurate End-to-End Speech Recognition in Joint CTC/Attention Frames

Chengdong Liang, Xiao-Lei Zhang, Binbin Zhang, Di Wu, Shengqiang Li, Xingchen Song +2

ICASSP 2023accepted

Recently, the unified streaming and non-streaming two-pass (U2/U2++) end-to-end model for speech recognition has shown great performance in terms of streaming capability, accuracy and latency. In this paper, we present fast-U2++, an enhanced version of U2++ to further reduce partial latency. The cor…

Cited by 0 Source ↗Scholar ↗

2021

Transformer-Based End-to-End Speech Recognition with Local Dense Synthesizer Attention

Menglong Xu, Shengqiang Li, Xiao-Lei Zhang

ICASSP 2021accepted

Recently, several studies reported that dot-product self-attention (SA) may not be indispensable to the state-of-the-art Transformer models. Motivated by the fact that dense synthesizer attention (DSA), which dispenses with dot products and pairwise interactions, achieved competitive results in many…

Cited by 0 Source ↗Scholar ↗