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.

Generating natural listener responses in conversational scenarios is crucial for creating engaging digital humans and avatars. Recent work has shown that large language models (LLMs) can be effectively leveraged for this task, demonstrating remarkable capabilities in generating contextually appropriate listener behaviors. However, current LLM-based methods face two critical limitations: they rely solely on speech content, overlooking other crucial communication signals, and they entangle listener identity with response generation, compromising output fidelity and generalization. In this work, we present a novel framework that addresses these limitations while maintaining the advantages of LLMs. Our approach introduces a Multimodal-LM architecture that jointly processes speech content, acoustics, and speaker emotion, capturing the full spectrum of communication cues. Additionally, we propose an identity disentanglement strategy using instance normalization and adaptive instance normalization in a VQ-VAE framework, enabling high-fidelity listening head synthesis with flexible identity control. Extensive experiments demonstrate that our method significantly outperforms existing approaches in terms of response naturalness and fidelity, while enabling effective identity control without retraining.

Trust region optimization-based received signal strength indicator (RSSI) interference source localization methods have been widely used in low-altitude research. However, these methods often converge to local optima in complex environments, degrading the positioning performance. This paper presents a novel unmanned aerial vehicle (UAV)-aided progressive interference source localization method based on improved trust region optimization. By combining the Levenberg-Marquardt (LM) algorithm with particle swarm optimization (PSO), our proposed method can effectively enhance the success rate of localization. We also propose a confidence quantification approach based on the UAV-to-ground channel model. This approach considers the surrounding environmental information of the sampling points and dynamically adjusts the weight of the sampling data during the data fusion. As a result, the overall positioning accuracy can be significantly improved. Experimental results demonstrate the proposed method can achieve high-precision interference source localization in noisy and interference-prone environments.

Unmanned aerial vehicle (UAV) communication is a promising part of next generation mobile communication network. Path loss (PL) is vital for the communication quality, where vegetation penetration loss (VPL) is a critical factor under UAV-to-ground (U2G) scenarios. In this paper, we propose a VPL model considering the foliage density and moisture content, and a measurement system is developed and implemented to acquire a large amount of channel data for fitting model parameters. Measurement results show that the proposed VPL model is more accurate and universal compared with typical models such as COST-235 and FITU-R. The proposed model and measurement results can provide a valuable reference for U2G communication in vegetation scenarios.

A realistic channel model is vital for designing, optimizing, and evaluating unmanned aerial vehicle (UAV)-to-ground (U2G) communication systems. This paper presents a comprehensive U2G ultra-wideband (UWB) channel model by considering the large-scale fading (LSF), including path loss (PL), shadow fading (SF), and airframe shadowing (AS). The effects of carrier frequency, bandwidth, building distribution, and UAV airframe structure on the LSF are fully studied. Different from the traditional bandwidth-independent PL calculation method, an extended closed-form expression for calculating PL is proposed to capture the new characteristics of ultra-wide bandwidth. The SF part is statistically described by a parametric lognormal model, and the built-up scenario-dependent parameters are predicted by a hybrid method with the ray-tracing and virtual scenario technologies. In addition, the AS part with respect to the airframe structure and posture variation is derived. It consists of the direct and reflected path components which are obtained by the deterministic and statistical approaches, respectively. The numerical simulations show that bandwidth, building distribution, and airframe structure have great influence on the LSF characteristics. For example, the fluctuation of received power can reach 30 dB due to the AS. The proposed model also shows its effectiveness and reliability by comparing with the RT and measured data, as well as the good compatibility with standardized models for some typical scenarios.

Effective beam alignment is essential for vehicle-to-infrastructure (V2I) millimeter wave (mmWave) communication systems, particularly in high-mobility vehicle scenarios. This paper explores a three-dimensional (3D) vehicle environment and introduces a novel deep learning (DL)-based beam search method that incorporates an image-based coding (IBC) technique. The mmWave beam search is approached as an image processing problem based on situational awareness. We propose IBC to leverage the locations, sizes, and information of vehicles, and utilize convolutional neural network (CNN) to train the image dataset. Consequently, the optimal beam pair index(BPI)can be determined. Simulation results demonstrate that the proposed beam search method achieves satisfactory performance in terms of accuracy and robustness compared to conventional methods.

Generating talking face videos from audio attracts lots of research interest. A few person-specific methods can generate vivid videos but require the target speaker's videos for training or fine-tuning. Existing person-generic methods have difficulty in generating realistic and lip-synced videos while preserving identity information. To tackle this problem, we propose a two-stage framework consisting of audio-to-landmark generation and landmark-to-video rendering procedures. First, we devise a novel Transformer-based landmark generator to infer lip and jaw landmarks from the audio. Prior landmark characteristics of the speaker's face are employed to make the generated landmarks coincide with the facial outline of the speaker. Then, a video rendering model is built to translate the generated landmarks into face images. During this stage, prior appearance information is extracted from the lower-half occluded target face and static reference images, which helps generate realistic and identity-preserving visual content. For effectively exploring the prior information of static reference images, we align static reference images with the target face's pose and expression based on motion fields. Moreover, auditory features are reused to guarantee that the generated face images are well synchronized with the audio. Extensive experiments demonstrate that our method can produce more realistic, lip-synced, and identity-preserving videos than existing person-generic talking face generation methods.

This paper proposes a general unmanned aerial vehicle (UAV)-to-ground (U2G) channel model. The proposed model is consistent with real scenarios by considering the impacts of flight altitude and UAV posture on channel gain. Machine learning and ray tracing (RT) techniques are employed to improve the generation method of altitude-dependent parameters, i.e., path loss (PL) and shadow fading (SF). In addition, posture-related fuselage shadowing coefficient (FSC) is introduced to modify the channel gain, and three-dimensional (3D) geometry modeling of the fuselage is conducted to calculate the FSC. Numerical simulation results show that the flight altitude and UAV posture have obvious effects on channel gain. The proposed model with modified channel gain can effectively describe the PL, SF, and received power under fuselage shadowing. The validity and advantage of the improved channel gain are verified by comparing the simulation results with the measured ones.

Abstract Spectrum resources are becoming harder to come by for wireless communications. The spectrum environment map (SEM), which depicts the electromagnetic environment's current state and future trend, is a valuable technique for managing and allocating spectrum resources. Most SEM construction approaches only take static SEMs into account and cannot forecast time‐domain changes and trends of SEMs in dynamic scenes. In this paper, a brand‐new temporal SEM prediction method for the high dynamic spectrum environment is proposed. This method is based on knowledge of radiation source and the optical flow driven by propagation channel models. First, a novel radiation source localization strategy is designed to obtain the radiation source movement information. Then, the optical flow field of the available SEMs is combined with the information regarding radiation source movement. In order to forecast future SEMs, a propagation model driven reconstruction technique is developed. Simulation findings demonstrate how well the suggested strategy is tailored to capture the spatiotemporal correlation of SEMs. This technique performs better than the state‐of‐the‐art in terms of single‐ and multiple‐step SEM predictions.

In the task of talking head generation, it is hard to learn the mapping relationship between generated head image and input audio signal. To tackle this challenge, we propose to learn the mapping relationship between input audio signal and the parameters of three-dimensional morphable face model (3DMM) first, which is easier to learn. Then the parameters of 3DMM are used to guide the generation of high-quality talking head images. Prior works mostly encode audio features from short audio windows, which may influence the accuracy of lip movements sometimes because of the limited context. In this paper, we propose a transformer-based audio encoder to take full use of the long-term context from audio and then predict a sequence of 3DMM parameters accurately. Unlike prior works that only use the 3DMM parameters of expression, rotation and translation, we propose to include the parameters of identity. Since the location of 3D facial mesh point is decided by the expression and identity parameters, it is helpful to supply more subtle control of lip movement by considering the identity parameters. The experimental results reveal that our method ranks first in 4 of the total 11 evaluation metrics, which ranks first in the talking head generation track.

A general empirical path loss (PL) model for air-to-ground (A2G) millimeter-wave (mmWave) channels is proposed in this paper. Different from existing PL models, the new model takes the height factor of unmanned aerial vehicles (UAVs) into account, and divides the propagation conditions into three cases (i.e., line-of-sight, reflection, and diffraction). A map-based deterministic PL prediction algorithm based on the ray-tracing (RT) technique is developed, and is used to generate numerous PL data for different cases. By fitting and analyzing the PL data under different scenarios and UAV heights, altitude-dependent model parameters are provided. Simulation results show that the proposed model can be effectively used to predict PL values for both low- and high-altitude cases. The prediction results of the proposed model better match the RT-based calculation results than those of the Third Generation Partnership Project (3GPP) model and the close-in model. The standard deviation of the PL is also much smaller. Moreover, the new model is flexible and can be extended to other A2G scenarios (not included in this paper) by adjusting the parameters according to the simulation or measurement data.

Based on the geometry and ray tracing (RT) theory, a millimeter wave (mmWave) channel model and parameter computation method for unmanned aerial vehicle (UAV) assisted air-to-ground (A2G) communications are proposed in this paper. In order to speed up the parameter calculation, a reconstruction process of scene database on the original digital map is developed. Moreover, the effects of reconstruction accuracy on the channel parameter and characteristic are analyzed by extensive simulations at 28 GHz under the campus scene. The simulation and analysis results show that the simplified database can save up to 50% time consumption. However, the difference of statistical properties is slight in the campus scenario.