[HTML][HTML] Deepfakes as a threat to a speaker and facial recognition: An overview of tools and attack vectors

A Firc, K Malinka, P Hanáček - Heliyon, 2023 - cell.com
Deepfakes present an emerging threat in cyberspace. Recent developments in machine
learning make deepfakes highly believable, and very difficult to differentiate between what is …

Voice conversion challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversion

Y Zhao, WC Huang, X Tian, J Yamagishi… - arXiv preprint arXiv …, 2020 - arxiv.org
The voice conversion challenge is a bi-annual scientific event held to compare and
understand different voice conversion (VC) systems built on a common dataset. In 2020, we …

[PDF][PDF] Cross-Lingual Voice Conversion with a Cycle Consistency Loss on Linguistic Representation.

Y Zhou, X Tian, Z Wu, H Li - Interspeech, 2021 - isca-archive.org
Abstract Cross-Lingual Voice Conversion (XVC) aims to modify a source speaker identity
towards a target while preserving the source linguistic content. This paper introduces a cycle …

Attentions for Short Duration Speech Classification

H Modi, M Patel, HA Patil - 2023 31st European Signal …, 2023 - ieeexplore.ieee.org
Neural attention mechanisms have gained significant popularity and widespread adoption in
various applications. These attention mechanisms can be applied to different models …

[PDF][PDF] A hybrid CNN-LSTM model with adaptive instance normalization for one shot singing voice conversion

A Yousuf, DS George - AIMS Electronics and Electrical Engineering, 2024 - aimspress.com
Singing voice conversion methods encounter challenges in achieving a delicate balance
between synthesis quality and singer similarity. Traditional voice conversion techniques …

IVCGAN: An Improved GAN for Voice Conversion

W Zhao, W Wang, J Chai… - 2021 IEEE 5th Information …, 2021 - ieeexplore.ieee.org
In the task of voice conversion (VC), the voice of the source speaker is converted into the
voice of the target speaker, but the voice content does not change in this task. There has …

Speech generation by generative adversarial network

Y Chen - 2021 2nd International Conference on Big Data & …, 2021 - ieeexplore.ieee.org
This paper takes a review of some recent state-of-the-art works in the field of speech
generation through adopting adaptive Generative Adversarial Network (GAN). It firstly …

[PDF][PDF] Comparison and Development of Practical Voice Conversion Models

M Baas - 2020 - rf5.github.io
Voice conversion (VC) is a speech processing task where speech by a source speaker is
transformed into speech that appears to be spoken by a desired target speaker while …