Zhong Meng, Jinyu Li, Yong Zhao, Yifan Gong, “Conditional teacher-student learning for model training,” US Patent 11,586,930, 2023.
Jinyu Li, Vadim Mazalov, Changliang, Liu, Liang Lu, Yifan Gong, “Layer trajectory long short-term memory with future context,” US Patent 11,631,399, 2023.
Amit Das, Jinyu Li, Changliang, Liu, Yifan Gong, “Universal acoustic modeling using neural mixture models,” US Patent 11,676,006, 2023.
Guoli Ye, Yan Huang, Wenning Wei, Lei He, Eva Sharma, Jian Wu, Yao Tiao; Edward Lin, Yifan Gong, Rui Zhao, Jinyu Li, “Generating and using text-to-speech data for speech recognition models,” US Patent 11,587,569, 2023.
Zhong Meng, Yashesh Gaur, Jinyu Li, Yifan Gong, “Speaker adaptation for attention-based encoder-decoder,” US Patent 11,232,782, 2022.
Jinyu Li, Michael Seltzer, Xi Wang, Rui Zhao, Yifan Gong, “Domain adaptation in speech recognition via teacher-student learning,” US Patent 10,885,900, 2021.
Jinyu Li, Guoli Ye, Rui Zhao, Yifan Gong, Ke Li, “Code-switching speech recognition with end-to-end connectionist temporal classification model,” US Patent 10,964,309, 2021.
Jinyu Li, Yifan Gong, Yongqiang Wang, “Small-footprint deep neural network,” US Patent 10,515,301, 2019.
Jinyu Li, Rui Zhao, Yifan Gong, “Variable-component deep neural network for robust speech recognition,” US Patent 10,019,990, 2018.
Jian Xue, Emilian Stoimenov, Jinyu Li, Yifan Gong, “Restructuring deep neural network acoustic models,” US Patent 9,728,184, 2017.
Jui-Ting Huang, Jinyu Li, Dong Yu, Li Deng, Yifan Gong, “Multilingual deep neural network,” US Patent 9,842,585, 2017.
Jinyu Li, Yifan Gong, Chaojun Liu, Kaisheng Yao, “Model training for automatic speech recognition from imperfect transcription data,” US Patent 9,280,969, 2016.
Jian Xue, Jinyu Li, Dong Yu, Michael Seltzer, Yifan Gong, “Low-footprint adaptation and personalization for a deep neural network,” US Patent 9,324,321, 2016.
Jinyu Li, Zhijie Yan, Qiang Huo, Yifan Gong, “Posterior-based feature with partial distance elimination for speech recognition,” US Patent 9,336,775, 2016.
Jinyu Li, Dong Yu, Yifan Gong, “Exploiting heterogeneous data in deep neural network-based speech recognition systems,” US Patent 9,454,958, 2016.
Jinyu Li, Jian Xue, Yifan Gong, “Shared hidden layer combination for speech recognition systems,” US Patent 9,520,127, 2016.
Dong Yu, Li Deng, Jinyu Li, “Confidence calibration in automatic speech recognition systems,” US Patent 9,070,360, 2015.
Li Deng, Jinyu Li, Dong Yu, Yifan Gong, “Online distorted speech estimation within an unscented transformation framework,” US Patent 8,731,916, 2014.
Dong Yu, Li Deng, Alex Acero, Yifan Gong, Jinyu Li, “High performance HMM adaptation with joint compensation of additive and convolutive distortions,” US Patent 8,180,637, 2012.
Jinyu Li, Li Deng, Dong Yu, Yifan Gong, Alex Acero, “Phase sensitive model adaptation for noisy speech recognition,” US Patent 8,214,215, 2012.
Jinyu Li, Li Deng, Dong Yu, Jian Wu, Yifan Gong, Alex Acero, “Adapting a compressed model for use in speech recognition,” US Patent 8,239,195, 2012.