no code implementations • 9 Jul 2022 • Jicheng Zhang, Yizhou Peng, HaiHua Xu, Yi He, Eng Siong Chng, Hao Huang
Intermediate layer output (ILO) regularization by means of multitask training on encoder side has been shown to be an effective approach to yielding improved results on a wide range of end-to-end ASR frameworks.
no code implementations • 9 Jul 2022 • Yizhou Peng, Yufei Liu, Jicheng Zhang, HaiHua Xu, Yi He, Hao Huang, Eng Siong Chng
More importantly, we train an end-to-end (E2E) speech recognition model by means of merging two monolingual data sets and observe the efficacy of the proposed ILME-based LM fusion for CSSR.
no code implementations • 7 Oct 2021 • Yizhou Peng, Jicheng Zhang, HaiHua Xu, Hao Huang, Eng Siong Chng
Non-autoregressive end-to-end ASR framework might be potentially appropriate for code-switching recognition task thanks to its inherent property that present output token being independent of historical ones.
no code implementations • 15 Jun 2021 • Jicheng Zhang, Yizhou Peng, Pham Van Tung, HaiHua Xu, Hao Huang, Eng Siong Chng
In this paper, we propose a single multi-task learning framework to perform End-to-End (E2E) speech recognition (ASR) and accent recognition (AR) simultaneously.
no code implementations • 21 Jan 2021 • Xiangyun Zeng, XiaoFeng Wang, Ali Esamdin, Craig Pellegrino, WeiKang Zheng, Jujia Zhang, Jun Mo, Wenxiong Li, D. Andrew Howell, Alexei V. Filippenko, Han Lin, Thomas G. Brink, Edward A. Baron, Jamison Burke, James M. DerKacy, Curtis McCully, Daichi Hiramatsu, Griffin Hosseinzadeh, Benjamin T. Jeffers, Timothy W. Ross, Benjamin E. Stahl, Samantha Stegman, Stefano Valenti, Lifan Wang, Danfeng Xiang, Jicheng Zhang, Tianmeng Zhang
We present extensive, well-sampled optical and ultraviolet photometry and optical spectra of the Type Ia supernova (SN Ia) 2017hpa.
High Energy Astrophysical Phenomena Solar and Stellar Astrophysics
no code implementations • 22 Oct 2020 • Yizhou Peng, Jicheng Zhang, Haobo Zhang, HaiHua Xu, Hao Huang, Eng Siong Chng
Experimental results on an 8-accent English speech recognition show both methods can yield WERs close to the conventional ASR systems that completely ignore the accent, as well as desired AR accuracy.