Related papers: FluentLip: A Phonemes-Based Two-stage Approach for…
Real-time video dubbing that preserves identity consistency while achieving accurate lip synchronization remains a critical challenge. Existing approaches face a trilemma: diffusion-based methods achieve high visual fidelity but suffer from…
Most lip-to-speech (LTS) synthesis models are trained and evaluated under the assumption that the audio-video pairs in the dataset are perfectly synchronized. In this work, we show that the commonly used audio-visual datasets, such as GRID,…
Video editing-based talking face generation aims to preserve video details such as pose, lighting, and gestures while modifying only lip motion, often using an identity reference image to maintain speaker consistency. However, this…
Most audio-visual speaker extraction methods rely on synchronized lip recording to isolate the speech of a target speaker from a multi-talker mixture. However, in natural human communication, co-speech gestures are also temporally aligned…
Despite recent advances in syncing lip movements with any audio waves, current methods still struggle to balance generation quality and the model's generalization ability. Previous studies either require long-term data for training or…
The task of few-shot visual dubbing focuses on synchronizing the lip movements with arbitrary speech input for any talking head video. Albeit moderate improvements in current approaches, they commonly require high-quality homologous data…
Lip sync has emerged as a promising technique for generating mouth movements from audio signals. However, synthesizing a high-resolution and photorealistic virtual news anchor is still challenging. Lack of natural appearance, visual…
As a key component of talking face generation, lip movements generation determines the naturalness and coherence of the generated talking face video. Prior literature mainly focuses on speech-to-lip generation while there is a paucity in…
In this work, we revisit the effectiveness of 3DMM for talking head synthesis by jointly learning a 3D face reconstruction model and a talking head synthesis model. This enables us to obtain a FACS-based blendshape representation of facial…
In this paper, we introduce a novel approach to address the task of synthesizing speech from silent videos of any in-the-wild speaker solely based on lip movements. The traditional approach of directly generating speech from lip videos…
Lip reading, also known as visual speech recognition, aims to recognize the speech content from videos by analyzing the lip dynamics. There have been several appealing progress in recent years, benefiting much from the rapidly developed…
Language-queried audio source separation (LASS) focuses on separating sounds using textual descriptions of the desired sources. Current methods mainly use discriminative approaches, such as time-frequency masking, to separate target sounds…
Talking face generation with great practical significance has attracted more attention in recent audio-visual studies. How to achieve accurate lip synchronization is a long-standing challenge to be further investigated. Motivated by xxx, in…
Video dubbing requires content accuracy, expressive prosody, high-quality acoustics, and precise lip synchronization, yet existing approaches struggle on all four fronts. To address these issues, we propose DiFlowDubber, the first video…
In this work, we re-think the task of speech enhancement in unconstrained real-world environments. Current state-of-the-art methods use only the audio stream and are limited in their performance in a wide range of real-world noises. Recent…
Visual speaker recognition based on lip motion offers a silent, hands-free, and behavior-driven biometric solution that remains effective even when acoustic cues are unavailable. Compared to traditional methods that rely heavily on…
Given a piece of text, a video clip, and a reference audio, the movie dubbing task aims to generate speech that aligns with the video while cloning the desired voice. The existing methods have two primary deficiencies: (1) They struggle to…
Direct speech-to-speech translation achieves high-quality results through the introduction of discrete units obtained from self-supervised learning. This approach circumvents delays and cascading errors associated with model cascading.…
We aim to edit the lip movements in talking video according to the given speech while preserving the personal identity and visual details. The task can be decomposed into two sub-problems: (1) speech-driven lip motion generation and (2)…
Achieving high-fidelity lip-speech synchronization in audio-driven talking portrait synthesis remains challenging. While multi-stage pipelines or diffusion models yield high-quality results, they suffer from high computational costs. Some…