no code implementations • 26 Oct 2023 • Xinfa Zhu, Yuke Li, Yi Lei, Ning Jiang, Guoqing Zhao, Lei Xie
This paper aims to build a multi-speaker expressive TTS system, synthesizing a target speaker's speech with multiple styles and emotions.
no code implementations • 17 Sep 2023 • Jixun Yao, Yuguang Yang, Yi Lei, Ziqian Ning, Yanni Hu, Yu Pan, JingJing Yin, Hongbin Zhou, Heng Lu, Lei Xie
In this study, we propose PromptVC, a novel style voice conversion approach that employs a latent diffusion model to generate a style vector driven by natural language prompts.
no code implementations • 17 Aug 2023 • Bin Chen, Zhiwei Liang, Shen Li, Yi Lei, Gabriele Liga, Alex Alvarado
Multidimensional constellation shaping of up to 32 dimensions with different spectral efficiencies are compared through AWGN and fiber-optic simulations.
no code implementations • 29 Jul 2023 • Xinfa Zhu, Yi Lei, Tao Li, Yongmao Zhang, Hongbin Zhou, Heng Lu, Lei Xie
However, such data-efficient approaches have ignored synthesizing emotional aspects of speech due to the challenges of cross-speaker cross-lingual emotion transfer - the heavy entanglement of speaker timbre, emotion, and language factors in the speech signal will make a system produce cross-lingual synthetic speech with an undesired foreign accent and weak emotion expressiveness.
no code implementations • 14 Feb 2023 • Zhiwei Liang, Bin Chen, Yi Lei, Gabriele Liga, Alex Alvarado
As an application of our model, we further study the effects of signal-noise interactions in long-haul transmission via the proposed model.
no code implementations • 19 Nov 2022 • Xinfa Zhu, Yi Lei, Kun Song, Yongmao Zhang, Tao Li, Lei Xie
This paper aims to synthesize the target speaker's speech with desired speaking style and emotion by transferring the style and emotion from reference speech recorded by other speakers.
no code implementations • 6 Nov 2022 • Jixun Yao, Qing Wang, Yi Lei, Pengcheng Guo, Lei Xie, Namin Wang, Jie Liu
By directly scaling the formant and F0, the speaker distinguishability degradation of the anonymized speech caused by the introduction of other speakers is prevented.
no code implementations • 6 Nov 2022 • Jixun Yao, Yi Lei, Qing Wang, Pengcheng Guo, Ziqian Ning, Lei Xie, Hai Li, Junhui Liu, Danming Xie
Background sound is an informative form of art that is helpful in providing a more immersive experience in real-application voice conversion (VC) scenarios.
no code implementations • 15 Jun 2022 • Qicong Xie, Shan Yang, Yi Lei, Lei Xie, Dan Su
The ideal goal of voice conversion is to convert the source speaker's speech to sound naturally like the target speaker while maintaining the linguistic content and the prosody of the source speech.
no code implementations • 2 Jun 2022 • Zhiwei Liang, Bin Chen, Yi Lei, Gabriele Liga, Alex Alvarado
Nonlinear interference models for dual-polarization 4D (DP-4D) modulation have only been used so far to predict signal-signal nonlinear interference.
no code implementations • 23 Dec 2021 • Bin Chen, Gabriele Liga, Yi Lei, Wei Ling, Zhengyan Huan, Xuwei Xue, Alex Alvarado
We review the design of multidimensional modulations by maximizing generalized mutual information and compare the maximum transmission reach of recently introduced 4D formats.
no code implementations • 29 Oct 2021 • Bin Chen, Wei Ling, Yunus Can Gültekin, Yi Lei, Chigo Okonkwo, Alex Alvarado
Signal shaping is vital to approach Shannon's capacity, yet it is challenging to implement at very high speeds.