Multi-Domain Dialogue State Tracking with Top-K Slot Self Attention

no code implementations • SIGDIAL (ACL) 2022 • Longfei Yang, Jiyi Li, Sheng Li, Takahiro Shinozaki

In the slot self-attention layers, we force each slot to involve information from the other k prominent slots and mask the rest out.

Dialogue State Tracking Multi-domain Dialogue State Tracking +1

Generic Cryo-CMOS Device Modeling and EDACompatible Platform for Reliable Cryogenic IC Design

no code implementations • 10 Nov 2022 • Zhidong Tang, Zewei Wang, Yumeng Yuan, Chang He, Xin Luo, Ao Guo, Renhe Chen, Yongqi Hu, Longfei Yang, Chengwei Cao, Linlin Liu, Liujiang Yu, Ganbing Shang, Yongfeng Cao, Shoumian Chen, Yuhang Zhao, Shaojian Hu, Xufeng Kou

Furthermore, by incorporating the Cryo-CMOS compact model into the process design kit (PDK), the cryogenic 4 Kb SRAM, 5-bit flash ADC and 8-bit current steering DAC are designed, and their performance is readily investigated and optimized on the EDA-compatible platform, hence laying a solid foundation for large-scale cryogenic IC design.

Large-Scale End-to-End Multilingual Speech Recognition and Language Identification with Multi-Task Learning

1 code implementation • 25 Oct 2020 • Wenxin Hou, Yue Dong, Bairong Zhuang, Longfei Yang, Jiatong Shi, Takahiro Shinozaki

In this paper, we report a large-scale end-to-end language-independent multilingual model for joint automatic speech recognition (ASR) and language identification (LID).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

CTM: Collaborative Temporal Modeling for Action Recognition

no code implementations • 8 Feb 2020 • Qian Liu, Tao Wang, Jie Liu, Yang Guan, Qi Bu, Longfei Yang

In order to learn powerful feature of videos, we propose a Collaborative Temporal Modeling (CTM) block (Figure 1) to learn temporal information for action recognition.

Action Recognition Video Understanding