no code implementations • 23 Feb 2024 • Jintao Jiang, Yingbo Gao, Mohammad Zeineldeen, Zoltan Tuske
In this paper, alternating weak triphone/BPE alignment supervision is proposed to improve end-to-end model training.
no code implementations • 24 Nov 2023 • Jintao Jiang, Yingbo Gao, Zoltan Tuske
In contrast to the general one-hot cross-entropy losses, here we use a cross-entropy loss with a label smoothing parameter to regularize the supervision.
no code implementations • 20 Jan 2023 • Beomyeol Jeon, Linda Cai, Chirag Shetty, Pallavi Srivastava, Jintao Jiang, Xiaolan Ke, Yitao Meng, Cong Xie, Indranil Gupta
While these result in model placements that train fast on data (i. e., low step times), learning-based model-parallelism is time-consuming, taking many hours or days to create a placement plan of operators on devices.
no code implementations • 11 Nov 2021 • Zijian Yang, Yingbo Gao, Alexander Gerstenberger, Jintao Jiang, Ralf Schlüter, Hermann Ney
Compared to our previous work, the criteria considered in this work are self-normalized and there is no need to further conduct a correction step.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2