Shulin Feng — accepted AI-conference papers

2022

Speechmoe2: Mixture-of-Experts Model with Improved Routing

ICASSP 2022accepted

Mixture-of-experts based acoustic models with dynamic routing mechanisms have proved promising results for speech recognition. The design principle of router architecture is important for the large model capacity and high computational efficiency. Our previous work SpeechMoE only uses local grapheme…

Cited by 0 Source ↗Scholar ↗

2019

Learning Discriminative Features in Sequence Training without Requiring Framewise Labelled Data

Jun Wang, Dan Su, Jie Chen, Shulin Feng, Dongpeng Ma, Na Li +1

ICASSP 2019accepted

In this work, we try to answer two questions: Can deeply learned features with discriminative power benefit an ASR system’s robustness to acoustic variability? And how to learn them without requiring framewise labelled sequence training data? As existing methods usually require knowing where the lab…

Cited by 0 Source ↗Scholar ↗