no code implementations • 12 Feb 2024 • Tonglong Wei, Youfang Lin, Shengnan Guo, Yan Lin, Yiheng Huang, Chenyang Xiang, Yuqing Bai, Menglu Ya, Huaiyu Wan
In this paper, we propose a new problem to meet the practical application need, \emph{i. e.}, road network-constrained trajectory (RNTraj) generation, which can directly generate trajectories on the road network with road-related information.
no code implementations • 28 Oct 2020 • Xingchen Song, Zhiyong Wu, Yiheng Huang, Chao Weng, Dan Su, Helen Meng
Non-autoregressive (NAR) transformer models have achieved significantly inference speedup but at the cost of inferior accuracy compared to autoregressive (AR) models in automatic speech recognition (ASR).
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 23 Oct 2019 • Xingchen Song, Guangsen Wang, Zhiyong Wu, Yiheng Huang, Dan Su, Dong Yu, Helen Meng
Our best systems achieve a relative improvement of 11. 9% and 8. 3% on the TIMIT and WSJ tasks respectively.
no code implementations • 19 Sep 2019 • Yiheng Huang, Jinchuan Tian, Lei Han, Guangsen Wang, Xingcheng Song, Dan Su, Dong Yu
One important challenge of training an NNLM is to leverage between scaling the learning process and handling big data.
no code implementations • 2 Sep 2019 • Yiheng Huang, Liqiang He, Lei Han, Guangsen Wang, Dan Su
In this work, we propose to train pruned language models for the word classes to replace the slots in the root n-gram.
no code implementations • ICML 2018 • Lei Han, Yiheng Huang, Tong Zhang
This paper proposes a method for multi-class classification problems, where the number of classes K is large.