Zobrazeno 1 - 10
of 896
pro vyhledávání: '"Zhu Wenjing"'
Conformer-based attention models have become the de facto backbone model for Automatic Speech Recognition tasks. A blank symbol is usually introduced to align the input and output sequences for CTC or RNN-T models. Unfortunately, the long input lengt
Externí odkaz:
http://arxiv.org/abs/2403.08258
Publikováno v:
IEEE Transactions on Knowledge and Data Engineering early access (2024) 1-14
Reasoning, a crucial aspect of NLP research, has not been adequately addressed by prevailing models including Large Language Model. Conversation reasoning, as a critical component of it, remains largely unexplored due to the absence of a well-designe
Externí odkaz:
http://arxiv.org/abs/2305.17727
Our investigation into the Affective Reasoning in Conversation (ARC) task highlights the challenge of causal discrimination. Almost all existing models, including large language models (LLMs), excel at capturing semantic correlations within utterance
Externí odkaz:
http://arxiv.org/abs/2305.02615
Autor:
Zhu, Wenjing, Wang, XiaoLong
We determine the resonant parameters of the vector states $\phi(1680)$ and $\phi(2170)$, by doing a combined fit to the $e^{+}e^{-}\to \eta\phi$ cross sections from threshold to $2.85~\rm GeV$ measured by BaBar, Belle, BESIII and CMD-3 experiments. T
Externí odkaz:
http://arxiv.org/abs/2304.08001
Autor:
Zhu, Sujie1 (AUTHOR), Zhu, Wenjing2 (AUTHOR), Zhao, Kaihua3 (AUTHOR), Yu, Jie3 (AUTHOR), Lu, Wenxia4 (AUTHOR), Zhou, Rui5 (AUTHOR), Fan, Shule4 (AUTHOR), Kong, Weikaixin6,7,8 (AUTHOR) 1510307407@pku.edu.cn, Yang, Feifei4 (AUTHOR) bio_yangff@ujn.edu.cn, Shan, Peipei1 (AUTHOR) shanpeipei@qdu.edu.cn
Publikováno v:
Cell Communication & Signaling. 7/15/2024, Vol. 22 Issue 1, p1-24. 24p.
Transformer has shown advanced performance in speech separation, benefiting from its ability to capture global features. However, capturing local features and channel information of audio sequences in speech separation is equally important. In this p
Externí odkaz:
http://arxiv.org/abs/2303.03737
In noisy and reverberant environments, the performance of deep learning-based speech separation methods drops dramatically because previous methods are not designed and optimized for such situations. To address this issue, we propose a multi-stage en
Externí odkaz:
http://arxiv.org/abs/2303.03732
Autor:
Zhu, Wenjing, Li, Xiang
Speech Emotion Recognition (SER) is a fundamental task to predict the emotion label from speech data. Recent works mostly focus on using convolutional neural networks~(CNNs) to learn local attention map on fixed-scale feature representation by viewin
Externí odkaz:
http://arxiv.org/abs/2204.05571
Autor:
Liu, Xiaodan, Li, Wenjing, Yue, Zhiheng, Qian, Jiangjin, Zhu, Wenjing, Dai, Huang, Wang, Jiahua, Pi, Fuwei
Publikováno v:
In Food Chemistry: X 30 December 2024 24
Autor:
Wang, Weiwei, Chen, Linxia, Xu, Feipeng, Chen, Rihong, Li, Qidong, Zou, Lirui, Hu, Honghui, Zhu, Wenjing
Publikováno v:
In Heliyon 15 November 2024 10(21)