Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Menglong Xu

Menglong Xu

Conformer-based End-to-end Speech Recognition With Rotary Position Embedding

Jul 13, 2021
Shengqiang Li, Menglong Xu, Xiao-Lei Zhang

Figure 1 for Conformer-based End-to-end Speech Recognition With Rotary Position Embedding

Figure 2 for Conformer-based End-to-end Speech Recognition With Rotary Position Embedding

Figure 3 for Conformer-based End-to-end Speech Recognition With Rotary Position Embedding

Figure 4 for Conformer-based End-to-end Speech Recognition With Rotary Position Embedding

* 5 pages, 3 figures

Access Paper or Ask Questions

AUC Optimization for Robust Small-footprint Keyword Spotting with Limited Training Data

Jul 13, 2021
Menglong Xu, Shengqiang Li, Chengdong Liang, Xiao-Lei Zhang

Figure 1 for AUC Optimization for Robust Small-footprint Keyword Spotting with Limited Training Data

Figure 2 for AUC Optimization for Robust Small-footprint Keyword Spotting with Limited Training Data

Figure 3 for AUC Optimization for Robust Small-footprint Keyword Spotting with Limited Training Data

Figure 4 for AUC Optimization for Robust Small-footprint Keyword Spotting with Limited Training Data

* submitted to ASRU2021

Access Paper or Ask Questions

Efficient conformer-based speech recognition with linear attention

Apr 14, 2021
Shengqiang Li, Menglong Xu, Xiao-Lei Zhang

Figure 1 for Efficient conformer-based speech recognition with linear attention

Figure 2 for Efficient conformer-based speech recognition with linear attention

Figure 3 for Efficient conformer-based speech recognition with linear attention

Figure 4 for Efficient conformer-based speech recognition with linear attention

* 5 pages,4 figures

Access Paper or Ask Questions

Transformer-based end-to-end speech recognition with residual Gaussian-based self-attention

Apr 02, 2021
Chengdong Liang, Menglong Xu, Xiao-Lei Zhang

Access Paper or Ask Questions

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

Oct 23, 2020
Menglong Xu, Shengqiang Li, Xiao-Lei Zhang

Figure 1 for Transformer-based End-to-End Speech Recognition with Local Dense Synthesizer Attention

Figure 2 for Transformer-based End-to-End Speech Recognition with Local Dense Synthesizer Attention

Figure 3 for Transformer-based End-to-End Speech Recognition with Local Dense Synthesizer Attention

Figure 4 for Transformer-based End-to-End Speech Recognition with Local Dense Synthesizer Attention

* 5 pages, 3 figures

Access Paper or Ask Questions