Zobrazeno 1 - 10
of 232
pro vyhledávání: '"Su, Xiangdong"'
Recent studies have highlighted the effectiveness of tensor decomposition methods in the Temporal Knowledge Graphs Embedding (TKGE) task. However, we found that inherent heterogeneity among factor tensors in tensor decomposition significantly hinders
Externí odkaz:
http://arxiv.org/abs/2404.09155
Autor:
Luo, Yi, Lin, Zhenghao, Zhang, Yuhao, Sun, Jiashuo, Lin, Chen, Xu, Chengjin, Su, Xiangdong, Shen, Yelong, Guo, Jian, Gong, Yeyun
Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques includes principle-driven integration, but it faces challenges arising f
Externí odkaz:
http://arxiv.org/abs/2403.11838
Connectionist temporal classification (CTC) and attention-based encoder decoder (AED) joint training has been widely applied in automatic speech recognition (ASR). Unlike most hybrid models that separately calculate the CTC and AED losses, our propos
Externí odkaz:
http://arxiv.org/abs/2308.08449
This paper presents a translation-based knowledge geraph embedding method via efficient relation rotation (TransERR), a straightforward yet effective alternative to traditional translation-based knowledge graph embedding models. Different from the pr
Externí odkaz:
http://arxiv.org/abs/2306.14580
Long-form numerical reasoning in financial analysis aims to generate a reasoning program to calculate the correct answer for a given question. Previous work followed a retriever-generator framework, where the retriever selects key facts from a long-f
Externí odkaz:
http://arxiv.org/abs/2212.07249
Autor:
Guo, Song1 (AUTHOR) sguo217@connect.hkust-gz.edu.cn, Su, Xiangdong1 (AUTHOR), Zhao, Hang1 (AUTHOR) hangzhao@hkust-gz.edu.cn
Publikováno v:
Energies (19961073). Aug2024, Vol. 17 Issue 16, p3864. 19p.
The vast majority of speech separation methods assume that the number of speakers is known in advance, hence they are specific to the number of speakers. By contrast, a more realistic and challenging task is to separate a mixture in which the number
Externí odkaz:
http://arxiv.org/abs/2203.16054
Publikováno v:
In Ceramics International 15 June 2024 50(12):21066-21073
Speech enhancement at extremely low signal-to-noise ratio (SNR) condition is a very challenging problem and rarely investigated in previous works. This paper proposes a robust speech enhancement approach (UNetGAN) based on U-Net and generative advers
Externí odkaz:
http://arxiv.org/abs/2010.15521
This paper proposes a full-band and sub-band fusion model, named as FullSubNet, for single-channel real-time speech enhancement. Full-band and sub-band refer to the models that input full-band and sub-band noisy spectral feature, output full-band and
Externí odkaz:
http://arxiv.org/abs/2010.15508