no code implementations • 21 Jun 2023 • Zhonghua Liu, Shijun Wang, Ning Chen
In this paper, we propose a VC model that can automatically disentangle speech into four components using only two augmentation functions, without the requirement of multiple hand-crafted features or laborious bottleneck tuning.
no code implementations • 9 Jun 2023 • Shijun Wang, Jón Guðnason, Damian Borth
Effective speech emotional representations play a key role in Speech Emotion Recognition (SER) and Emotional Text-To-Speech (TTS) tasks.
no code implementations • 2 Mar 2023 • Shijun Wang, Jón Guðnason, Damian Borth
State-of-the-art Text-To-Speech (TTS) models are capable of producing high-quality speech.
no code implementations • 21 Nov 2022 • Siqiao Xue, Xiaoming Shi, Hongyan Hao, Lintao Ma, Shiyu Wang, Shijun Wang, James Zhang
Point process is the dominant paradigm for modeling event sequences occurring at irregular intervals.
1 code implementation • 31 May 2022 • Siqiao Xue, Chao Qu, Xiaoming Shi, Cong Liao, Shiyi Zhu, Xiaoyu Tan, Lintao Ma, Shiyu Wang, Shijun Wang, Yun Hu, Lei Lei, Yangfei Zheng, Jianguo Li, James Zhang
Predictive autoscaling (autoscaling with workload forecasting) is an important mechanism that supports autonomous adjustment of computing resources in accordance with fluctuating workload demands in the Cloud.
no code implementations • 27 Oct 2021 • Shijun Wang, Dimche Kostadinov, Damian Borth
We then use the learned prosodic representations as conditional information to train and enhance our VC model for zero-shot conversion.
no code implementations • 13 Apr 2021 • Shijun Wang, Damian Borth
Voice conversion (VC) is a task that transforms voice from target audio to source without losing linguistic contents, it is challenging especially when source and target speakers are unseen during training (zero-shot VC).
no code implementations • 9 Jun 2020 • Baocheng Zhu, Shijun Wang, James Zhang
In this paper, by leveraging recent progresses in representation learning and state space models (SSMs), we propose NeurPhy, which uses variational auto-encoder (VAE) to extract underlying Markovian dynamic state at each time step, neural process (NP) to extract the global system parameters, and a non-linear non-recurrent stochastic state space model to learn the physical dynamic transition.
no code implementations • 19 May 2020 • Shijun Wang, Baocheng Zhu, Lintao Ma, Yuan Qi
In this paper, we consider optimizing a smooth, convex, lower semicontinuous function in Riemannian space with constraints.
no code implementations • 19 May 2020 • Shijun Wang, Baocheng Zhu, Chen Li, Mingzhe Wu, James Zhang, Wei Chu, Yuan Qi
In this paper, We propose a general Riemannian proximal optimization algorithm with guaranteed convergence to solve Markov decision process (MDP) problems.
no code implementations • 14 Aug 2014 • Ari Seff, Le Lu, Kevin M. Cherry, Holger Roth, Jiamin Liu, Shijun Wang, Joanne Hoffman, Evrim B. Turkbey, Ronald M. Summers
In this paper, we propose a new algorithm representation of decomposing the LN detection problem into a set of 2D object detection subtasks on sampled CT slices, largely alleviating the curse of dimensionality issue.
no code implementations • 6 Jun 2014 • Holger R. Roth, Le Lu, Ari Seff, Kevin M. Cherry, Joanne Hoffman, Shijun Wang, Jiamin Liu, Evrim Turkbey, Ronald M. Summers
and 84%/90% at 6 FP/vol.
no code implementations • NeurIPS 2009 • Rong Jin, Shijun Wang, Yang Zhou
In this paper, we examine the generalization error of regularized distance metric learning.