3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition

7 April 2022

Papers citing "3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition"

4 / 4 papers shown

Title
eMoE: Task-aware Memory Efficient Mixture-of-Experts-Based (MoE) Model Inference Suraiya Tairin Shohaib Mahmud Haiying Shen Anand Iyer MoE 126 0 0 10 Mar 2025
U2++ MoE: Scaling 4.7x parameters with minimal impact on RTF Xingchen Song Di Wu Binbin Zhang Dinghao Zhou Zhendong Peng Bo Dang Fuping Pan Chao Yang MoE 31 5 0 25 Apr 2024
Zipformer: A faster and better encoder for automatic speech recognition Zengwei Yao Liyong Guo Xiaoyu Yang Wei Kang Fangjun Kuang Yifan Yang Zengrui Jin Long Lin Daniel Povey VLM 25 64 0 17 Oct 2023
CIF-T: A Novel CIF-based Transducer Architecture for Automatic Speech Recognition Tian-Hao Zhang Dinghao Zhou Guiping Zhong Jiaming Zhou Baoxiang Li 10 3 0 26 Jul 2023