A review of deep learning techniques for speech processing

A Mehrish, N Majumder, R Bharadwaj, R Mihalcea… - Information …, 2023 - Elsevier
The field of speech processing has undergone a transformative shift with the advent of deep
learning. The use of multiple processing layers has enabled the creation of models capable …

Deepfakes generation and detection: State-of-the-art, open challenges, countermeasures, and way forward

M Masood, M Nawaz, KM Malik, A Javed, A Irtaza… - Applied …, 2023 - Springer
Easy access to audio-visual content on social media, combined with the availability of
modern tools such as Tensorflow or Keras, and open-source trained models, along with …

An overview of voice conversion and its challenges: From statistical modeling to deep learning

B Sisman, J Yamagishi, S King… - IEEE/ACM Transactions …, 2020 - ieeexplore.ieee.org
Speaker identity is one of the important characteristics of human speech. In voice
conversion, we change the speaker identity from one to another, while keeping the linguistic …

Contentvec: An improved self-supervised speech representation by disentangling speakers

K Qian, Y Zhang, H Gao, J Ni, CI Lai… - International …, 2022 - proceedings.mlr.press
Self-supervised learning in speech involves training a speech representation network on a
large-scale unannotated speech corpus, and then applying the learned representations to …

A review of synthetic image data and its use in computer vision

K Man, J Chahl - Journal of Imaging, 2022 - mdpi.com
Development of computer vision algorithms using convolutional neural networks and deep
learning has necessitated ever greater amounts of annotated and labelled data to produce …

Stargan-vc2: Rethinking conditional methods for stargan-based voice conversion

T Kaneko, H Kameoka, K Tanaka, N Hojo - arXiv preprint arXiv …, 2019 - arxiv.org
Non-parallel multi-domain voice conversion (VC) is a technique for learning mappings
among multiple domains without relying on parallel data. This is important but challenging …

A novel deep learning technique for morphology preserved fetal ECG extraction from mother ECG using 1D-CycleGAN

P Basak, AHMN Sakib, MEH Chowdhury… - Expert Systems with …, 2024 - Elsevier
The non-invasive fetal electrocardiogram (fECG) enables easy detection of developing heart
abnormalities, leading to a significant reduction in infant mortality rate and post-natal …

Again-vc: A one-shot voice conversion using activation guidance and adaptive instance normalization

YH Chen, DY Wu, TH Wu, H Lee - ICASSP 2021-2021 IEEE …, 2021 - ieeexplore.ieee.org
Recently, voice conversion (VC) has been widely studied. Many VC systems use
disentangle-based learning techniques to separate the speaker and the linguistic content …

Data augmentation for deep neural networks model in EEG classification task: a review

C He, J Liu, Y Zhu, W Du - Frontiers in Human Neuroscience, 2021 - frontiersin.org
Classification of electroencephalogram (EEG) is a key approach to measure the rhythmic
oscillations of neural activity, which is one of the core technologies of brain-computer …

Cyclegan-vc3: Examining and improving cyclegan-vcs for mel-spectrogram conversion

T Kaneko, H Kameoka, K Tanaka, N Hojo - arXiv preprint arXiv …, 2020 - arxiv.org
Non-parallel voice conversion (VC) is a technique for learning mappings between source
and target speeches without using a parallel corpus. Recently, cycle-consistent adversarial …