Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Tang, Benlai"'
Over the past decade, a series of unflagging efforts have been dedicated to developing highly expressive and controllable text-to-speech (TTS) systems. In general, the holistic TTS comprises two interconnected components: the frontend module and the
Externí odkaz:
http://arxiv.org/abs/2404.09192
Autor:
Zhong, Jinzuomu, Li, Yang, Huang, Hui, Richmond, Korin, Liu, Jie, Su, Zhiba, Guo, Jing, Tang, Benlai, Zhu, Fengjie
In expressive and controllable Text-to-Speech (TTS), explicit prosodic features significantly improve the naturalness and controllability of synthesised speech. However, manual prosody annotation is labor-intensive and inconsistent. To address this i
Externí odkaz:
http://arxiv.org/abs/2309.05423
Autor:
Liu, Jie, Su, Zhiba, Huang, Hui, Wan, Caiyan, Wang, Quanxiu, Hong, Jiangli, Tang, Benlai, Zhu, Fengjie
Thanks to recent advancements in end-to-end speech modeling technology, it has become increasingly feasible to imitate and clone a user`s voice. This leads to a significant challenge in differentiating between authentic and fabricated audio segments.
Externí odkaz:
http://arxiv.org/abs/2306.15212
Recently, talking face generation has drawn ever-increasing attention from the research community in computer vision due to its arduous challenges and widespread application scenarios, e.g. movie animation and virtual anchor. Although persevering eff
Externí odkaz:
http://arxiv.org/abs/2305.13962
Autor:
Xie, Tianyi, Liao, Liucheng, Bi, Cheng, Tang, Benlai, Yin, Xiang, Yang, Jianfei, Wang, Mingjie, Yao, Jiali, Zhang, Yang, Ma, Zejun
The task of few-shot visual dubbing focuses on synchronizing the lip movements with arbitrary speech input for any talking head video. Albeit moderate improvements in current approaches, they commonly require high-quality homologous data sources of v
Externí odkaz:
http://arxiv.org/abs/2201.06260
Clothes style transfer for person video generation is a challenging task, due to drastic variations of intra-person appearance and video scenarios. To tackle this problem, most recent AdaIN-based architectures are proposed to extract clothes and scen
Externí odkaz:
http://arxiv.org/abs/2110.11894
Recently, phonetic posteriorgrams (PPGs) based methods have been quite popular in non-parallel singing voice conversion systems. However, due to the lack of acoustic information in PPGs, style and naturalness of the converted singing voices are still
Externí odkaz:
http://arxiv.org/abs/2110.04754
Singing voice conversion (SVC) aims to convert the voice of one singer to that of other singers while keeping the singing content and melody. On top of recent voice conversion works, we propose a novel model to steadily convert songs while keeping th
Externí odkaz:
http://arxiv.org/abs/2010.14804
Autor:
Li, Wenjie, Tang, Benlai, Yin, Xiang, Zhao, Yushi, Li, Wei, Wang, Kang, Huang, Hao, Wang, Yuxuan, Ma, Zejun
Accent conversion (AC) transforms a non-native speaker's accent into a native accent while maintaining the speaker's voice timbre. In this paper, we propose approaches to improving accent conversion applicability, as well as quality. First of all, we
Externí odkaz:
http://arxiv.org/abs/2005.09271
Autor:
Gu, Yu, Yin, Xiang, Rao, Yonghui, Wan, Yuan, Tang, Benlai, Zhang, Yang, Chen, Jitong, Wang, Yuxuan, Ma, Zejun
This paper presents ByteSing, a Chinese singing voice synthesis (SVS) system based on duration allocated Tacotron-like acoustic models and WaveRNN neural vocoders. Different from the conventional SVS models, the proposed ByteSing employs Tacotron-lik
Externí odkaz:
http://arxiv.org/abs/2004.11012