no code implementations • 3 Jun 2024 • Yongxin Zhu, Dan Su, Liqiang He, Linli Xu, Dong Yu
While recent advancements in speech language models have achieved significant progress, they face remarkable challenges in modeling the long acoustic sequences of neural audio codecs.
no code implementations • 15 Apr 2024 • Chong Peng, Liqiang He, Dan Su
Today, there have been many achievements in learning the association between voice and face.
1 code implementation • ICCV 2023 • Liqiang He, Wei Wang, Albert Chen, Min Sun, Cheng-Hao Kuo, Sinisa Todorovic
We propose a Bidirectional Alignment for domain adaptive Detection with Transformers (BiADT) to improve cross domain object detection performance.
no code implementations • CVPR 2022 • Liqiang He, Sinisa Todorovic
Second, we use a mini-detector to initialize the content queries in the decoder with classification and regression embeddings of the respective heads in the mini-detector.
no code implementations • 8 May 2021 • Liqiang He, Shulin Feng, Dan Su, Dong Yu
Extensive experiments show that: 1) Based on the proposed neural architecture, the neural networks with a medium latency of 550ms (millisecond) and a low latency of 190ms can be learned in the vanilla and revised operation space respectively.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 25 Aug 2020 • Liqiang He, Dan Su, Dong Yu
Extensive experiments show that: (i) the architecture searched on the small proxy dataset can be transferred to the large dataset for the speech recognition tasks.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
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.