no code implementations • 27 Aug 2021 • Zhen Huang, Xiaodan Zhuang, Daben Liu, Xiaoqiang Xiao, Yuchen Zhang, Sabato Marco Siniscalchi
To achieve such an ambitious goal, new mechanisms for foreign pronunciation generation and language model (LM) enrichment have been devised.
no code implementations • 7 Dec 2020 • Xinwei Li, Yuanyuan Zhang, Xiaodan Zhuang, Daben Liu
We demonstrate that f-SpecAugment is more effective than the utterance level SpecAugment for deep CNN based hybrid models.
no code implementations • 4 Oct 2019 • Zhen Huang, Tim Ng, Leo Liu, Henry Mason, Xiaodan Zhuang, Daben Liu
The most popular way to train very deep CNNs is to use shortcut connections (SC) together with batch normalization (BN).