Generative adversarial networks (GANs) have seen remarkable progress in recent years. They are used as generative models for all kinds of data such as text, images, audio, music …
We present the latest iteration of the voice conversion challenge (VCC) series, a bi-annual scientific event aiming to compare and understand different voice conversion (VC) systems …
Z Khanjani, G Watson, VP Janeja - Frontiers in Big Data, 2023 - frontiersin.org
A deepfake is content or material that is synthetically generated or manipulated using artificial intelligence (AI) methods, to be passed off as real and can include audio, video …
K Zhou, B Sisman, H Li - arXiv preprint arXiv:2002.00198, 2020 - arxiv.org
Emotional voice conversion aims to convert the spectrum and prosody to change the emotional patterns of speech, while preserving the speaker identity and linguistic content …
S Liu, Y Cao, D Su, H Meng - 2021 IEEE Automatic Speech …, 2021 - ieeexplore.ieee.org
Singing voice conversion (SVC) is one promising technique that can enrich the way of human-computer interaction by en-dowing a computer the ability to produce high-fidelity and …
K Zhou, B Sisman, H Li - 2021 IEEE spoken language …, 2021 - ieeexplore.ieee.org
Emotional voice conversion (EVC) aims to convert the emotion of speech from one state to another while preserving the linguistic content and speaker identity. In this paper, we study …
The term “differentiable digital signal processing” describes a family of techniques in which loss function gradients are backpropagated through digital signal processors, facilitating …
S Liu, Y Cao, N Hu, D Su… - 2021 ieee international …, 2021 - ieeexplore.ieee.org
This paper presents FastSVC, a light-weight cross-domain singing voice conversion (SVC) system, which can achieve high conversion performance, with inference speed 4x faster …
YJ Luo, CC Hsu, K Agres… - ICASSP 2020-2020 IEEE …, 2020 - ieeexplore.ieee.org
We propose a flexible framework that deals with both singer conversion and singers vocal technique conversion. The proposed model is trained on non-parallel corpora …