activity
20192026
most citedSpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts

5 citations · 7 across the 5 of their papers we have counts for

collaborators
Showing eess.ASShow all

2 papers · 1 filter

eess.AS2021

SpeechMoE2: Mixture-of-Experts Model with Improved Routing

Zhao You, Shulin Feng, Dan Su +1

Mixture-of-experts based acoustic models with dynamic routing mechanisms have proved promising results for speech recognition. The design principle of router architecture is import…

eess.AS2021

Latency-Controlled Neural Architecture Search for Streaming Speech Recognition

Liqiang He, Shulin Feng, Dan Su +1

Neural architecture search (NAS) has attracted much attention and has been explored for automatic speech recognition (ASR). In this work, we focus on streaming ASR scenarios and pr…