Zobrazeno 1 - 10
of 10 105
pro vyhledávání: '"Sun Chang"'
Autor:
Sun, Chang, Qin, Bo
Target speaker extraction (TSE) is a technique for isolating a target speaker's voice from mixed speech using auxiliary features associated with the target speaker. It is another attempt at addressing the cocktail party problem and is generally consi
Externí odkaz:
http://arxiv.org/abs/2411.13811
Autor:
Hafner, Flavio, Sun, Chang
Synthetic data generators, when trained using privacy-preserving techniques like differential privacy, promise to produce synthetic data with formal privacy guarantees, facilitating the sharing of sensitive data. However, it is crucial to empirically
Externí odkaz:
http://arxiv.org/abs/2411.12451
Autor:
Yuan, Hong, Sun, Chang-Pu
To address the observation of Max Born (M. Born 1969) that the Newton's second law can emerge from a purely statistical perspective, we derive the evolution equation about the statistical distribution for dilute gas based solely on statistical princi
Externí odkaz:
http://arxiv.org/abs/2410.14094
Autor:
Hu, Guimin, Xin, Yi, Lyu, Weimin, Huang, Haojian, Sun, Chang, Zhu, Zhihong, Gui, Lin, Cai, Ruichu, Cambria, Erik, Seifi, Hasti
Multimodal affective computing (MAC) has garnered increasing attention due to its broad applications in analyzing human behaviors and intentions, especially in text-dominated multimodal affective computing field. This survey presents the recent trend
Externí odkaz:
http://arxiv.org/abs/2409.07388
Publikováno v:
IEEE Signal Processing Letters, 2024
In point cloud geometry compression, most octreebased context models use the cross-entropy between the onehot encoding of node occupancy and the probability distribution predicted by the context model as the loss. This approach converts the problem o
Externí odkaz:
http://arxiv.org/abs/2407.08528
Publikováno v:
IEEE Journal on Emerging and Selected Topics in Circuits and Systems, vol. 14, no. 2, pp. 224-234, Jun. 2024
In point cloud geometry compression, context models usually use the one-hot encoding of node occupancy as the label, and the cross-entropy between the one-hot encoding and the probability distribution predicted by the context model as the loss functi
Externí odkaz:
http://arxiv.org/abs/2407.08520
Autor:
Ibrahim, Mahmoud, Khalil, Yasmina Al, Amirrajab, Sina, Sun, Chang, Breeuwer, Marcel, Pluim, Josien, Elen, Bart, Ertaylan, Gokhan, Dumontier, Michel
This paper presents a comprehensive systematic review of generative models (GANs, VAEs, DMs, and LLMs) used to synthesize various medical data types, including imaging (dermoscopic, mammographic, ultrasound, CT, MRI, and X-ray), text, time-series, an
Externí odkaz:
http://arxiv.org/abs/2407.00116
Autor:
Li, Rui, Liu, Huai, Poon, Pak-Lok, Towey, Dave, Sun, Chang-Ai, Zheng, Zheng, Zhou, Zhi Quan, Chen, Tsong Yueh
Metamorphic testing has become one mainstream technique to address the notorious oracle problem in software testing, thanks to its great successes in revealing real-life bugs in a wide variety of software systems. Metamorphic relations, the core comp
Externí odkaz:
http://arxiv.org/abs/2406.05397
Model size and inference speed at deployment time, are major challenges in many deep learning applications. A promising strategy to overcome these challenges is quantization. However, a straightforward uniform quantization to very low precision can r
Externí odkaz:
http://arxiv.org/abs/2405.00645
Visual Speech Recognition (VSR) tasks are generally recognized to have a lower theoretical performance ceiling than Automatic Speech Recognition (ASR), owing to the inherent limitations of conveying semantic information visually. To mitigate this cha
Externí odkaz:
http://arxiv.org/abs/2403.18843