Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Qi, Tianhua"'
Realistic emotional voice conversion (EVC) aims to enhance emotional diversity of converted audios, making the synthesized voices more authentic and natural. To this end, we propose Emotional Intensity-aware Network (EINet), dynamically adjusting int
Externí odkaz:
http://arxiv.org/abs/2407.14800
Autor:
Li, Sunan, Lian, Hailun, Lu, Cheng, Zhao, Yan, Qi, Tianhua, Yang, Hao, Zong, Yuan, Zheng, Wenming
The emotion recognition has attracted more attention in recent decades. Although significant progress has been made in the recognition technology of the seven basic emotions, existing methods are still hard to tackle compound emotion recognition that
Externí odkaz:
http://arxiv.org/abs/2407.12973
In this paper, we propose Prosody-aware VITS (PAVITS) for emotional voice conversion (EVC), aiming to achieve two major objectives of EVC: high content naturalness and high emotional naturalness, which are crucial for meeting the demands of human per
Externí odkaz:
http://arxiv.org/abs/2403.01494
Publikováno v:
In Expert Systems With Applications 15 December 2024 258
Publikováno v:
Proceedings of SPIE; December 2021, Vol. 12087 Issue: 1 p120870I-120870I-8, 1087839p
Publikováno v:
Proceedings of SPIE; 2/23/2022, Vol. 12087, p120870I-120870I-8, 1p