Zobrazeno 1 - 10
of 124
pro vyhledávání: '"Liu, Hexin"'
Autor:
Zhang, Xiangyu, Zhang, Qiquan, Liu, Hexin, Xiao, Tianyi, Qian, Xinyuan, Ahmed, Beena, Ambikairajah, Eliathamby, Li, Haizhou, Epps, Julien
Transformer and its derivatives have achieved success in diverse tasks across computer vision, natural language processing, and speech processing. To reduce the complexity of computations within the multi-head self-attention mechanism in Transformer,
Externí odkaz:
http://arxiv.org/abs/2405.12609
Autor:
Zhao, Qingchang, Li, Hancheng, Tao, Lian, Feng, Hua, Zhang, Shuangnan, Walter, Roland, Ge, Mingyu, Tong, Hao, Ji, Long, Zhang, Liang, Qu, Jinlu, Huang, Yue, Ma, Xiang, Zhang, Shu, Yin, Qianqing, Yin, Hongxing, Ma, Ruican, Zhao, Shujie, Li, Panping, Yang, Zixu, Liu, Hexin, Yu, Wei, Huang, Yiming, Li, Zexi, Li, Yajun, Xiao, Jingyu, Zhao, Kang
We conduct a comprehensive analysis of the accreting X-ray pulsar, Hercules X-1, utilizing data from IXPE and NuSTAR. IXPE performed five observations of Her X-1, consisting of three in the Main-on state and two in the Short-on state. Our time-resolv
Externí odkaz:
http://arxiv.org/abs/2405.00509
Autor:
Liu, Hexin, Zhang, Xiangyu, Garcia, Leibny Paola, Khong, Andy W. H., Chng, Eng Siong, Watanabe, Shinji
Code-switching (CS) refers to the switching of languages within a speech signal and results in language confusion for automatic speech recognition (ASR). To address language confusion, we propose the language alignment loss that performs frame-level
Externí odkaz:
http://arxiv.org/abs/2403.05887
Autor:
Jin, Pei, Zhang, Guobao, Zhang, Yuexin, Méndez, Mariano, Qu, Jinlu, Russell, David M., Wang, Jiancheng, Zhang, Shuangnan, Yang, Yi-Jung, Jia, Shumei, Yang, Zixu, Liu, Hexin
We present a detailed analysis of the observations with the Hard X-ray Modulation Telescope of the black hole X-ray transient 4U~1543-47 during its outburst in 2021. We find a clear state transition during the outburst decay of the source. Using prev
Externí odkaz:
http://arxiv.org/abs/2403.02874
Autor:
Zhang, Xiangyu, Liu, Hexin, Xu, Kaishuai, Zhang, Qiquan, Liu, Daijiao, Ahmed, Beena, Epps, Julien
Depression is a critical concern in global mental health, prompting extensive research into AI-based detection methods. Among various AI technologies, Large Language Models (LLMs) stand out for their versatility in mental healthcare applications. How
Externí odkaz:
http://arxiv.org/abs/2402.13276
Autor:
Zhang, Xiangyu, Liu, Daijiao, Liu, Hexin, Zhang, Qiquan, Meng, Hanyu, Garcia, Leibny Paola, Chng, Eng Siong, Yao, Lina
Recently, Denoising Diffusion Probabilistic Models (DDPMs) have attained leading performances across a diverse range of generative tasks. However, in the field of speech synthesis, although DDPMs exhibit impressive performance, their long training du
Externí odkaz:
http://arxiv.org/abs/2402.10642
Autor:
Ma, Ruican, Tao, Lian, Méndez, Mariano, Zhang, Shuang-Nan, Xu, Yanjun, Zhang, Liang, Liu, Hexin, Qu, Jinlu, Song, Liming, Ren, Xiaoqin, Zhao, Shujie, Huang, Yue, Ma, Xiang, Zhao, Qingchang, Xu, Yingchen, Li, Panping, Yang, Zixu, Yu, Wei
We analyzed an observation with the Nuclear Spectroscopic Telescope Array of the black-hole X-ray binary MAXI J1535-571 in the soft intermediate state, in which we detected a 2.5-ks long flare. Our spectral fitting results suggest that MAXI J1535-571
Externí odkaz:
http://arxiv.org/abs/2401.11466
Autor:
Yu, Wei, Bu, Qingcui, Doroshenko, Victor, Ducci, Lorenzo, Ji, Long, Zhang, Wenda, Santangelo, Andrea, Zhang, Shuangnan, Waghmare, Anand, Ge, Mingyu, Huang, Yue, Liu, Hexin, Tao, Lian, Yang, Zixu, Zhang, Liang, Qu, Jinlu
Context. In September 2022, the transient neutron star low-mass X-ray binary XTE J1701-462 went into a new outburst. Aims. The objective of this work is to examine the evolution of the accretion geometry of XTE J1701-462 by studying the spectro-polar
Externí odkaz:
http://arxiv.org/abs/2401.02658
Autor:
Chen, Chen, Hu, Yuchen, Yang, Chao-Han Huck, Liu, Hexin, Siniscalchi, Sabato Marco, Chng, Eng Siong
Code-switching (CS) speech refers to the phenomenon of mixing two or more languages within the same sentence. Despite the recent advances in automatic speech recognition (ASR), CS-ASR is still a challenging task ought to the grammatical structure com
Externí odkaz:
http://arxiv.org/abs/2310.13013
Languages usually switch within a multilingual speech signal, especially in a bilingual society. This phenomenon is referred to as code-switching (CS), making automatic speech recognition (ASR) challenging under a multilingual scenario. We propose to
Externí odkaz:
http://arxiv.org/abs/2309.16953