An overview of deep-learning-based audio-visual speech enhancement and separation

D Michelsanti, ZH Tan, SX Zhang, Y Xu… - … on Audio, Speech …, 2021 - ieeexplore.ieee.org
Speech enhancement and speech separation are two related tasks, whose purpose is to
extract either one or more target speech signals, respectively, from a mixture of sounds …

Lip to speech synthesis with visual context attentional gan

M Kim, J Hong, YM Ro - Advances in Neural Information …, 2021 - proceedings.neurips.cc
In this paper, we propose a novel lip-to-speech generative adversarial network, Visual
Context Attentional GAN (VCA-GAN), which can jointly model local and global lip …

End-to-end video-to-speech synthesis using generative adversarial networks

R Mira, K Vougioukas, P Ma, S Petridis… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
Video-to-speech is the process of reconstructing the audio speech from a video of a spoken
utterance. Previous approaches to this task have relied on a two-step process where an …

Analyzing lower half facial gestures for lip reading applications: Survey on vision techniques

SJ Preethi - Computer Vision and Image Understanding, 2023 - Elsevier
Lip reading has gained popularity due to the proliferation of emerging real-world
applications. This article provides a comprehensive review of benchmark datasets available …

[PDF][PDF] SVTS: scalable video-to-speech synthesis

R Mira, A Haliassos, S Petridis… - arXiv preprint …, 2022 - opus.bibliothek.uni-augsburg.de
Video-to-speech synthesis (also known as lip-to-speech) refers to the translation of silent lip
movements into the corresponding audio. This task has received an increasing amount of …

Nautilus: a versatile voice cloning system

HT Luong, J Yamagishi - IEEE/ACM Transactions on Audio …, 2020 - ieeexplore.ieee.org
We introduce a novel speech synthesis system, called NAUTILUS, that can generate speech
with a target voice either from a text input or a reference utterance of an arbitrary source …

Speechin: A smart necklace for silent speech recognition

R Zhang, M Chen, B Steeper, Y Li, Z Yan… - Proceedings of the …, 2021 - dl.acm.org
This paper presents SpeeChin, a smart necklace that can recognize 54 English and 44
Chinese silent speech commands. A customized infrared (IR) imaging system is mounted on …

[HTML][HTML] A robust voice spoofing detection system using novel CLS-LBP features and LSTM

H Dawood, S Saleem, F Hassan, A Javed - Journal of King Saud University …, 2022 - Elsevier
Abstract Automatic Speaker Verification (ASV) systems are vulnerable to a variety of voice
spoofing attacks, eg, replays, speech synthesis, etc. The imposters/fraudsters often use …

Lip-to-speech synthesis in the wild with multi-task learning

M Kim, J Hong, YM Ro - ICASSP 2023-2023 IEEE International …, 2023 - ieeexplore.ieee.org
Recent studies have shown impressive performance in Lip-to-speech synthesis that aims to
reconstruct speech from visual information alone. However, they have been suffering from …

Audio-visual speech inpainting with deep learning

G Morrone, D Michelsanti, ZH Tan… - ICASSP 2021-2021 …, 2021 - ieeexplore.ieee.org
In this paper, we present a deep-learning-based framework for audio-visual speech
inpainting, ie, the task of restoring the missing parts of an acoustic speech signal from …