Audio-driven talking face generation is a challenging task in digital communication. Despite significant progress in the area, most existing methods concentrate on audio-lip synchronization, often overlooking aspects such as visual quality, customization, and generalization that are crucial to producing realistic talking faces. To address these limitations, we introduce a novel, customizable one-shot audio-driven talking face generation framework, named PortraitTalk. Our proposed method utilizes a latent diffusion framework consisting of two main components: IdentityNet and AnimateNet. IdentityNet is designed to preserve identity features consistently across the generated video frames, while AnimateNet aims to enhance temporal coherence and motion consistency. This framework also integrates an audio input with the reference images, thereby reducing the reliance on reference-style videos prevalent in existing approaches. A key innovation of PortraitTalk is the incorporation of text prompts through decoupled cross-attention mechanisms, which significantly expands creative control over the generated videos. Through extensive experiments, including a newly developed evaluation metric, our model demonstrates superior performance over the state-of-the-art methods, setting a new standard for the generation of customizable realistic talking faces suitable for real-world applications.

Audio-driven lip sync has recently drawn significant attention due to its widespread application in the multimedia domain. Individuals exhibit distinct lip shapes when speaking the same utterance, attributed to the unique speaking styles of individuals, posing a notable challenge for audio-driven lip sync. Earlier methods for such task often bypassed the modeling of personalized speaking styles, resulting in sub-optimal lip sync conforming to the general styles. Recent lip sync techniques attempt to guide the lip sync for arbitrary audio by aggregating information from a style reference video, yet they can not preserve the speaking styles well due to their inaccuracy in style aggregation. This work proposes an innovative audio-aware style reference scheme that effectively leverages the relationships between input audio and reference audio from style reference video to address the style-preserving audio-driven lip sync. Specifically, we first develop an advanced Transformer-based model adept at predicting lip motion corresponding to the input audio, augmented by the style information aggregated through cross-attention layers from style reference video. Afterwards, to better render the lip motion into realistic talking face video, we devise a conditional latent diffusion model, integrating lip motion through modulated convolutional layers and fusing reference facial images via spatial cross-attention layers. Extensive experiments validate the efficacy of the proposed approach in achieving precise lip sync, preserving speaking styles, and generating high-fidelity, realistic talking face videos.

Audio-driven talking face video generation has attracted increasing attention due to its huge industrial potential. Some previous methods focus on learning a direct mapping from audio to visual content. Despite progress, they often struggle with the ambiguity of the mapping process, leading to flawed results. An alternative strategy involves facial structural representations (e.g., facial landmarks) as intermediaries. This multi-stage approach better preserves the appearance details but suffers from error accumulation due to the independent optimization of different stages. Moreover, most previous methods rely on generative adversarial networks, prone to training instability and mode collapse. To address these challenges, our study proposes a novel landmark-based diffusion model for talking face generation, which leverages facial landmarks as intermediate representations while enabling end-to-end optimization. Specifically, we first establish the less ambiguous mapping from audio to landmark motion of lip and jaw. Then, we introduce an innovative conditioning module called TalkFormer to align the synthesized motion with the motion represented by landmarks via differentiable cross-attention, which enables end-to-end optimization for improved lip synchronization. Besides, TalkFormer employs implicit feature warping to align the reference image features with the target motion for preserving more appearance details. Extensive experiments demonstrate that our approach can synthesize high-fidelity and lip-synced talking face videos, preserving more subject appearance details from the reference image.

Recent years have witnessed an exponential increase in the demand for face video compression, and the success of artificial intelligence has expanded the boundaries beyond traditional hybrid video coding. Generative coding approaches have been identified as promising alternatives with reasonable perceptual rate-distortion trade-offs, leveraging the statistical priors of face videos. However, the great diversity of distortion types in spatial and temporal domains, ranging from the traditional hybrid coding frameworks to generative models, present grand challenges in compressed face video quality assessment (VQA) that plays a crucial role in the whole delivery chain for quality monitoring and optimization. In this paper, we introduce the large-scale Compressed Face Video Quality Assessment (CFVQA) database, which is the first attempt to systematically understand the perceptual quality and diversified compression distortions in face videos. The database contains 3,240 compressed face video clips in multiple compression levels, which are derived from 135 source videos with diversified content using six representative video codecs, including two traditional methods based on hybrid coding frameworks, two end-to-end methods, and two generative methods. The unique characteristics of CFVQA, including large-scale, fine-grained, great content diversity, and cross-compression distortion types, make the benchmarking for existing image quality assessment (IQA) and VQA feasible and practical. The results reveal the weakness of existing IQA and VQA models, which challenge real-world face video applications. In addition, a FAce VideO IntegeRity (FA VOR) index for face video compression was developed to measure the perceptual quality, considering the distinct content characteristics and temporal priors of the face videos. Experimental results exhibit its superior performance on the proposed CFVQA dataset. ACE video based services have been growing exponentially, coinciding with the accelerated proliferation of mobile communication and online video content sharing platforms. Face video compression towards human vision, which is indispensable in compressing and delivering gigantic-scale face video data, introduces visual distortions inevitably. During the past decade, advancements in video compression technology have quintessentially benefited face video compression.

Forced alignment refers to a technology that time-aligns a given transcription with a corresponding speech. However, as the forced alignment technologies have developed using speech audio, they might fail in alignment when the input speech audio is noise-corrupted or is not accessible. We focus on that there is another component that the speech can be inferred from, the speech video (i.e., talking face video). Since the drawbacks of audio-based forced alignment can be complemented using the visual information when the audio signal is under poor condition, we try to develop a novel video-based forced alignment method. However, different from audio forced alignment, it is challenging to develop a reliable visual forced alignment technology for the following two reasons: 1) Visual Speech Recognition (VSR) has a much lower performance compared to audio-based Automatic Speech Recognition (ASR), and 2) the translation from text to video is not reliable, so the method typically used for building audio forced alignment cannot be utilized in developing visual forced alignment. In order to alleviate these challenges, in this paper, we propose a new method that is appropriate for visual forced alignment, namely Deep Visual Forced Alignment (DVFA). The proposed DVFA can align the input transcription (i.e., sentence) with the talking face video without accessing the speech audio. Moreover, by augmenting the alignment task with anomaly case detection, DVFA can detect mismatches between the input transcription and the input video while performing the alignment. Therefore, we can robustly align the text with the talking face video even if there exist error words in the text. Through extensive experiments, we show the effectiveness of the proposed DVFA not only in the alignment task but also in interpreting the outputs of VSR models.

We propose an end-to-end framework to measure people's vital signs including Heart Rate (HR), Heart Rate Variability (HRV), Oxygen Saturation (SpO2) and Blood Pressure (BP) based on the rPPG methodology from the video of a user's face captured with a smartphone camera. We extract face landmarks with a deep learning-based neural network model in real-time. Multiple face patches also called Regions-of-Interest (RoIs) are extracted by using the predicted face landmarks. Several filters are applied to reduce the noise from the RoIs in the extracted cardiac signals called Blood Volume Pulse (BVP) signal. The measurements of HR, HRV and SpO2 are validated on two public rPPG datasets namely the TokyoTech rPPG and the Pulse Rate Detection (PURE) datasets, on which our models achieved the following Mean Absolute Errors (MAE): a) for HR, 1.73Beats-Per-Minute (bpm) and 3.95bpm respectively; b) for HRV, 18.55ms and 25.03ms respectively, and c) for SpO2, an MAE of 1.64% on the PURE dataset. We validated our end-to-end rPPG framework, ReViSe, in daily living environment, and thereby created the Video-HR dataset. Our HR estimation model achieved an MAE of 2.49bpm on this dataset. Since no publicly available rPPG datasets existed for BP measurement with face videos, we used a dataset with signals from fingertip sensor to train our deep learning-based BP estimation model and also created our own video dataset, Video-BP. On our Video-BP dataset, our BP estimation model achieved an MAE of 6.7mmHg for Systolic Blood Pressure (SBP), and an MAE of 9.6mmHg for Diastolic Blood Pressure (DBP). ReViSe framework has been validated on datasets with videos recorded in daily living environment as opposed to less noisy laboratory environment as reported by most state-of-the-art techniques.

While previous speech-driven talking face generation methods have made significant progress in improving the visual quality and lip-sync quality of the synthesized videos, they pay less attention to lip motion jitters which greatly undermine the realness of talking face videos. What causes motion jitters, and how to mitigate the problem? In this paper, we conduct systematic analyses on the motion jittering problem based on a state-of-the-art pipeline that uses 3D face representations to bridge the input audio and output video, and improve the motion stability with a series of effective designs. We find that several issues can lead to jitters in synthesized talking face video: 1) jitters from the input 3D face representations; 2) training-inference mismatch; 3) lack of dependency modeling among video frames. Accordingly, we propose three effective solutions to address this issue: 1) we propose a gaussian-based adaptive smoothing module to smooth the 3D face representations to eliminate jitters in the input; 2) we add augmented erosions on the input data of the neural renderer in training to simulate the distortion in inference to reduce mismatch; 3) we develop an audio-fused transformer generator to model dependency among video frames. Besides, considering there is no off-the-shelf metric for measuring motion jitters in talking face video, we devise an objective metric (Motion Stability Index, MSI), to quantitatively measure the motion jitters by calculating the reciprocal of variance acceleration. Extensive experimental results show the superiority of our method on motion-stable face video generation, with better quality than previous systems.

With a surge in online medical advising remote monitoring of patient vitals is required. This can be facilitated with the Remote Photoplethysmography (rPPG) techniques that compute vital signs from facial videos. It involves processing video frames to obtain skin pixels, extracting the cardiac data from it and applying signal processing filters to extract the Blood Volume Pulse (BVP) signal. Different algorithms are applied to the BVP signal to estimate the various vital signs. We implemented a web application framework to measure a person's Heart Rate (HR), Heart Rate Variability (HRV), Oxygen Saturation (SpO2), Respiration Rate (RR), Blood Pressure (BP), and stress from the face video. The rPPG technique is highly sensitive to illumination and motion variation. The web application guides the users to reduce the noise due to these variations and thereby yield a cleaner BVP signal. The accuracy and robustness of the framework was validated with the help of volunteers.

The goal of this work is to reconstruct speech from a silent talking face video. Recent studies have shown impressive performance on synthesizing speech from silent talking face videos. However, they have not explicitly considered on varying identity characteristics of different speakers, which place a challenge in the video-to-speech synthesis, and this becomes more critical in unseen-speaker settings. Our approach is to separate the speech content and the visage-style from a given silent talking face video. By guiding the model to independently focus on modeling the two representations, we can obtain the speech of high intelligibility from the model even when the input video of an unseen subject is given. To this end, we introduce speech-visage selection that separates the speech content and the speaker identity from the visual features of the input video. The disentangled representations are jointly incorporated to synthesize speech through visage-style based synthesizer which generates speech by coating the visage-styles while maintaining the speech content. Thus, the proposed framework brings the advantage of synthesizing the speech containing the right content even with the silent talking face video of an unseen subject. We validate the effectiveness of the proposed framework on the GRID, TCD-TIMIT volunteer, and LRW datasets.