1 code implementation • COLING 2022 • Xuhui Sui, Ying Zhang, Kehui Song, Baohang Zhou, Guoqing Zhao, Xin Wei, Xiaojie Yuan
Recently, zero-shot entity linking task has become a research hotspot, which links mentions to unseen entities to challenge the generalization ability.
no code implementations • 19 Mar 2024 • Zhigang Chen, Benjia Zhou, Jun Li, Jun Wan, Zhen Lei, Ning Jiang, Quan Lu, Guoqing Zhao
Although some approaches work towards gloss-free SLT through jointly training the visual encoder and translation network, these efforts still suffer from poor performance and inefficient use of the powerful Large Language Model (LLM).
Ranked #4 on
Gloss-free Sign Language Translation
on PHOENIX14T
no code implementations • 15 Dec 2023 • Ziqian Wang, Xinfa Zhu, Zihan Zhang, YuanJun Lv, Ning Jiang, Guoqing Zhao, Lei Xie
Given the intrinsic similarity between speech generation and speech enhancement, harnessing semantic information holds potential advantages for speech enhancement tasks.
no code implementations • 26 Oct 2023 • Xinfa Zhu, Yuke Li, Yi Lei, Ning Jiang, Guoqing Zhao, Lei Xie
This paper aims to build a multi-speaker expressive TTS system, synthesizing a target speaker's speech with multiple styles and emotions.
no code implementations • 7 Oct 2023 • Ze Li, Yuke Lin, Ning Jiang, Xiaoyi Qin, Guoqing Zhao, Haiying Wu, Ming Li
Utilizing the pseudo-labeling algorithm with large-scale unlabeled data becomes crucial for semi-supervised domain adaptation in speaker verification tasks.
1 code implementation • 25 Sep 2023 • Yuke Lin, Xiaoyi Qin, Ning Jiang, Guoqing Zhao, Ming Li
It is widely acknowledged that discriminative representation for speaker verification can be extracted from verbal speech.
no code implementations • 17 Aug 2023 • Ze Li, Yuke Lin, Xiaoyi Qin, Ning Jiang, Guoqing Zhao, Ming Li
For Track 1, we utilize a network structure based on ResNet for training.
no code implementations • 15 Aug 2023 • Ming Cheng, Weiqing Wang, Xiaoyi Qin, Yuke Lin, Ning Jiang, Guoqing Zhao, Ming Li
This paper describes the DKU-MSXF submission to track 4 of the VoxCeleb Speaker Recognition Challenge 2023 (VoxSRC-23).
no code implementations • 14 Aug 2023 • Yuke Lin, Xiaoyi Qin, Guoqing Zhao, Ming Cheng, Ning Jiang, Haiyang Wu, Ming Li
In this paper, we introduce a large-scale and high-quality audio-visual speaker verification dataset, named VoxBlink.
1 code implementation • COLING 2022 • Zichen Liu, Xuyuan Liu, Yanlong Wen, Guoqing Zhao, Fen Xia, Xiaojie Yuan
However, most previous works ignore the decisive information contained in structured medical data in EHRs, which is hard to be captured from the noisy clinical notes.
no code implementations • 22 Feb 2023 • Jiaming Zhou, Shiwan Zhao, Ning Jiang, Guoqing Zhao, Yong Qin
Unsupervised domain adaptation (UDA) aims to improve the performance on the unlabeled target domain by transferring knowledge from the source to the target domain.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
1 code implementation • 17 Oct 2022 • Yu Zhao, Xiangrui Cai, Yike Wu, Haiwei Zhang, Ying Zhang, Guoqing Zhao, Ning Jiang
Based on these embeddings, in the inference phase, we first make modality-split predictions and then exploit various ensemble methods to combine the predictions with different weights, which models the modality importance dynamically.
1 code implementation • COLING 2022 • Yike Wu, Yu Zhao, Shiwan Zhao, Ying Zhang, Xiaojie Yuan, Guoqing Zhao, Ning Jiang
In this work, we define the training instances with the same question type but different answers as \textit{superficially similar instances}, and attribute the language priors to the confusion of VQA model on such instances.
no code implementations • CVPR 2022 • Wei Li, Haiwei Zhang, Qijie Bai, Guoqing Zhao, Ning Jiang, Xiaojie Yuan
However, the application value of SG on downstream tasks is severely limited by the predicate classification bias, which is caused by long-tailed data and presented as semantic bias of predicted relation predicates.
1 code implementation • 25 Oct 2021 • Wei Wang, Yu Zhou, Jiahao Lv, Dayan Wu, Guoqing Zhao, Ning Jiang, Weiping Wang
The research focus of scene text detection and recognition has shifted to arbitrary shape text in recent years, where the text shape representation is a fundamental problem.
Ranked #5 on
Text Spotting
on SCUT-CTW1500