Yingfeng Yu

Yinfeng Yu, Lele Cao, Fuchun Sun et al. · tsinghua

Audio-visual embodied navigation, as a hot research topic, aims training a robot to reach an audio target using egocentric visual (from the sensors mounted on the robot) and audio (emitted from the target) input. The audio-visual information fusion strategy is naturally important to the navigation performance, but the state-of-the-art methods still simply concatenate the visual and audio features, potentially ignoring the direct impact of context. Moreover, the existing approaches requires either phase-wise training or additional aid (e.g. topology graph and sound semantics). Up till this date, the work that deals with the more challenging setup with moving target(s) is still rare. As a result, we propose an end-to-end framework FSAAVN (feature self-attention audio-visual navigation) to learn chasing after a moving audio target using a context-aware audio-visual fusion strategy implemented as a self-attention module. Our thorough experiments validate the superior performance (both quantitatively and qualitatively) of FSAAVN in comparison with the state-of-the-arts, and also provide unique insights about the choice of visual modalities, visual/audio encoder backbones and fusion patterns.

Alimjan Mattursun, Liejun Wang, Yinfeng Yu

Speech self-supervised learning (SSL) represents has achieved state-of-the-art (SOTA) performance in multiple downstream tasks. However, its application in speech enhancement (SE) tasks remains immature, offering opportunities for improvement. In this study, we introduce a novel cross-domain feature fusion and multi-attention speech enhancement network, termed BSS-CFFMA, which leverages self-supervised embeddings. BSS-CFFMA comprises a multi-scale cross-domain feature fusion (MSCFF) block and a residual hybrid multi-attention (RHMA) block. The MSCFF block effectively integrates cross-domain features, facilitating the extraction of rich acoustic information. The RHMA block, serving as the primary enhancement module, utilizes three distinct attention modules to capture diverse attention representations and estimate high-quality speech signals. We evaluate the performance of the BSS-CFFMA model through comparative and ablation studies on the VoiceBank-DEMAND dataset, achieving SOTA results. Furthermore, we select three types of data from the WHAMR! dataset, a collection specifically designed for speech enhancement tasks, to assess the capabilities of BSS-CFFMA in tasks such as denoising only, dereverberation only, and simultaneous denoising and dereverberation. This study marks the first attempt to explore the effectiveness of self-supervised embedding-based speech enhancement methods in complex tasks encompassing dereverberation and simultaneous denoising and dereverberation. The demo implementation of BSS-CFFMA is available online\footnote[2]{https://github.com/AlimMat/BSS-CFFMA. \label{s1}}.

Alimjan Mattursun, Liejun Wang, Yinfeng Yu et al.

Speech self-supervised learning (SSL) has made great progress in various speech processing tasks, but there is still room for improvement in speech enhancement (SE). This paper presents BSP-MPNet, a dual-path framework that combines self-supervised features with magnitude-phase information for SE. The approach starts by applying the perceptual contrast stretching (PCS) algorithm to enhance the magnitude-phase spectrum. A magnitude-phase 2D coarse (MP-2DC) encoder then extracts coarse features from the enhanced spectrum. Next, a feature-separating self-supervised learning (FS-SSL) model generates self-supervised embeddings for the magnitude and phase components separately. These embeddings are fused to create cross-domain feature representations. Finally, two parallel RNN-enhanced multi-attention (REMA) mask decoders refine the features, apply them to the mask, and reconstruct the speech signal. We evaluate BSP-MPNet on the VoiceBank+DEMAND and WHAMR! datasets. Experimental results show that BSP-MPNet outperforms existing methods under various noise conditions, providing new directions for self-supervised speech enhancement research. The implementation of the BSP-MPNet code is available online\footnote[2]{https://github.com/AlimMat/BSP-MPNet. \label{s1}}

Tao Zheng, Liejun Wang, Yinfeng Yu

Self-supervised learning has demonstrated impressive performance in speech tasks, yet there remains ample opportunity for advancement in the realm of speech enhancement research. In addressing speech tasks, confining the attention mechanism solely to the temporal dimension poses limitations in effectively focusing on critical speech features. Considering the aforementioned issues, our study introduces a novel speech enhancement framework, HFSDA, which skillfully integrates heterogeneous spatial features and incorporates a dual-dimension attention mechanism to significantly enhance speech clarity and quality in noisy environments. By leveraging self-supervised learning embeddings in tandem with Short-Time Fourier Transform (STFT) spectrogram features, our model excels at capturing both high-level semantic information and detailed spectral data, enabling a more thorough analysis and refinement of speech signals. Furthermore, we employ the innovative Omni-dimensional Dynamic Convolution (ODConv) technology within the spectrogram input branch, enabling enhanced extraction and integration of crucial information across multiple dimensions. Additionally, we refine the Conformer model by enhancing its feature extraction capabilities not only in the temporal dimension but also across the spectral domain. Extensive experiments on the VCTK-DEMAND dataset show that HFSDA is comparable to existing state-of-the-art models, confirming the validity of our approach.

Xinxin Jiao, Liejun Wang, Yinfeng Yu

Speech emotion recognition is crucial in human-computer interaction, but extracting and using emotional cues from audio poses challenges. This paper introduces MFHCA, a novel method for Speech Emotion Recognition using Multi-Spatial Fusion and Hierarchical Cooperative Attention on spectrograms and raw audio. We employ the Multi-Spatial Fusion module (MF) to efficiently identify emotion-related spectrogram regions and integrate Hubert features for higher-level acoustic information. Our approach also includes a Hierarchical Cooperative Attention module (HCA) to merge features from various auditory levels. We evaluate our method on the IEMOCAP dataset and achieve 2.6\% and 1.87\% improvements on the weighted accuracy and unweighted accuracy, respectively. Extensive experiments demonstrate the effectiveness of the proposed method.

Yi Wang, Yinfeng Yu, Fuchun Sun et al.

Audio-Visual Embodied Navigation aims to enable agents to autonomously navigate to sound sources in unknown 3D environments using auditory cues. While current AVN methods excel on in-distribution sound sources, they exhibit poor cross-source generalization: navigation success rates plummet and search paths become excessively long when agents encounter unheard sounds or unseen environments. This limitation stems from the lack of explicit alignment mechanisms between auditory signals and corresponding visual regions. Policies tend to memorize spurious \enquote{acoustic fingerprint-scenario} correlations during training, leading to blind exploration when exposed to novel sound sources. To address this, we propose the AGVP framework, which transforms sound from policy-memorable acoustic fingerprint cues into spatial guidance. The framework first extracts global auditory context via audio self-attention, then uses this context as queries to guide visual feature attention, highlighting sound-source-related regions at the feature level. Subsequent temporal modeling and policy optimization are then performed. This design, centered on interpretable cross-modal alignment and region reweighting, reduces dependency on specific acoustic fingerprints. Experimental results demonstrate that AGVP improves both navigation efficiency and robustness while achieving superior cross-scenario generalization on previously unheard sounds.

Tao Zhu, Yinfeng Yu, Liejun Wang et al.

Diffusion models have demonstrated remarkable performance in speech synthesis, but typically require multi-step sampling, resulting in low inference efficiency. Recent studies address this issue by distilling diffusion models into consistency models, enabling efficient one-step generation. However, these approaches introduce additional training costs and rely heavily on the performance of pre-trained teacher models. In this paper, we propose ECTSpeech, a simple and effective one-step speech synthesis framework that, for the first time, incorporates the Easy Consistency Tuning (ECT) strategy into speech synthesis. By progressively tightening consistency constraints on a pre-trained diffusion model, ECTSpeech achieves high-quality one-step generation while significantly reducing training complexity. In addition, we design a multi-scale gate module (MSGate) to enhance the denoiser's ability to fuse features at different scales. Experimental results on the LJSpeech dataset demonstrate that ECTSpeech achieves audio quality comparable to state-of-the-art methods under single-step sampling, while substantially reducing the model's training cost and complexity.

Tianheng Zhu, Yinfeng Yu, Liejun Wang et al.

This paper presents EGSTalker, a real-time audio-driven talking head generation framework based on 3D Gaussian Splatting (3DGS). Designed to enhance both speed and visual fidelity, EGSTalker requires only 3-5 minutes of training video to synthesize high-quality facial animations. The framework comprises two key stages: static Gaussian initialization and audio-driven deformation. In the first stage, a multi-resolution hash triplane and a Kolmogorov-Arnold Network (KAN) are used to extract spatial features and construct a compact 3D Gaussian representation. In the second stage, we propose an Efficient Spatial-Audio Attention (ESAA) module to fuse audio and spatial cues, while KAN predicts the corresponding Gaussian deformations. Extensive experiments demonstrate that EGSTalker achieves rendering quality and lip-sync accuracy comparable to state-of-the-art methods, while significantly outperforming them in inference speed. These results highlight EGSTalker's potential for real-time multimedia applications.

Jia Li, Yinfeng Yu, Liejun Wang et al.

In audio-visual navigation (AVN) tasks, an embodied agent must autonomously localize a sound source in unknown and complex 3D environments based on audio-visual signals. Existing methods often rely on static modality fusion strategies and neglect the spatial cues embedded in stereo audio, leading to performance degradation in cluttered or occluded scenes. To address these issues, we propose an end-to-end reinforcement learning-based AVN framework with two key innovations: (1) a \textbf{S}tereo-Aware \textbf{A}ttention \textbf{M}odule (\textbf{SAM}), which learns and exploits the spatial disparity between left and right audio channels to enhance directional sound perception; and (2) an \textbf{A}udio-\textbf{G}uided \textbf{D}ynamic \textbf{F}usion Module (\textbf{AGDF}), which dynamically adjusts the fusion ratio between visual and auditory features based on audio cues, thereby improving robustness to environmental changes. Extensive experiments are conducted on two realistic 3D scene datasets, Replica and Matterport3D, demonstrating that our method significantly outperforms existing approaches in terms of navigation success rate and path efficiency. Notably, our model achieves over 40\% improvement under audio-only conditions compared to the best-performing baselines. These results highlight the importance of explicitly modeling spatial cues from stereo channels and performing deep multi-modal fusion for robust and efficient audio-visual navigation.

Hailong Zhang, Yinfeng Yu, Liejun Wang et al.

Intelligent agents often require collaborative strategies to achieve complex tasks beyond individual capabilities in real-world scenarios. While existing audio-visual navigation (AVN) research mainly focuses on single-agent systems, their limitations emerge in dynamic 3D environments where rapid multi-agent coordination is critical, especially for time-sensitive applications like emergency response. This paper introduces MASTAVN (Multi-Agent Scalable Transformer Audio-Visual Navigation), a scalable framework enabling two agents to collaboratively localize and navigate toward an audio target in shared 3D environments. By integrating cross-agent communication protocols and joint audio-visual fusion mechanisms, MASTAVN enhances spatial reasoning and temporal synchronization. Through rigorous evaluation in photorealistic 3D simulators (Replica and Matterport3D), MASTAVN achieves significant reductions in task completion time and notable improvements in navigation success rates compared to single-agent and non-collaborative baselines. This highlights the essential role of spatiotemporal coordination in multi-agent systems. Our findings validate MASTAVN's effectiveness in time-sensitive emergency scenarios and establish a paradigm for advancing scalable multi-agent embodied intelligence in complex 3D environments.

Tianheng Zhu, Yinfeng Yu, Liejun Wang et al.

Audio-driven talking head generation is crucial for applications in virtual reality, digital avatars, and film production. While NeRF-based methods enable high-fidelity reconstruction, they suffer from low rendering efficiency and suboptimal audio-visual synchronization. This work presents PGSTalker, a real-time audio-driven talking head synthesis framework based on 3D Gaussian Splatting (3DGS). To improve rendering performance, we propose a pixel-aware density control strategy that adaptively allocates point density, enhancing detail in dynamic facial regions while reducing redundancy elsewhere. Additionally, we introduce a lightweight Multimodal Gated Fusion Module to effectively fuse audio and spatial features, thereby improving the accuracy of Gaussian deformation prediction. Extensive experiments on public datasets demonstrate that PGSTalker outperforms existing NeRF- and 3DGS-based approaches in rendering quality, lip-sync precision, and inference speed. Our method exhibits strong generalization capabilities and practical potential for real-world deployment.

Yubing Cao, Yinfeng Yu, Yongming Li et al.

This paper presents AMNet, an Acoustic Model Network designed to improve the performance of Mandarin speech synthesis by incorporating phrase structure annotation and local convolution modules. AMNet builds upon the FastSpeech 2 architecture while addressing the challenge of local context modeling, which is crucial for capturing intricate speech features such as pauses, stress, and intonation. By embedding a phrase structure parser into the model and introducing a local convolution module, AMNet enhances the model's sensitivity to local information. Additionally, AMNet decouples tonal characteristics from phonemes, providing explicit guidance for tone modeling, which improves tone accuracy and pronunciation. Experimental results demonstrate that AMNet outperforms baseline models in subjective and objective evaluations. The proposed model achieves superior Mean Opinion Scores (MOS), lower Mel Cepstral Distortion (MCD), and improved fundamental frequency fitting $F0 (R^2)$, confirming its ability to generate high-quality, natural, and expressive Mandarin speech.

Xuechun Shao, Yinfeng Yu, Liejun Wang

Multimodal emotion recognition (MER) seeks to integrate various modalities to predict emotional states accurately. However, most current research focuses solely on the fusion of audio and text features, overlooking the valuable information in emotion labels. This oversight could potentially hinder the performance of existing methods, as emotion labels harbor rich, insightful information that could significantly aid MER. We introduce a novel model called Label Signal-Guided Multimodal Emotion Recognition (LSGMER) to overcome this limitation. This model aims to fully harness the power of emotion label information to boost the classification accuracy and stability of MER. Specifically, LSGMER employs a Label Signal Enhancement module that optimizes the representation of modality features by interacting with audio and text features through label embeddings, enabling it to capture the nuances of emotions precisely. Furthermore, we propose a Joint Objective Optimization(JOO) approach to enhance classification accuracy by introducing the Attribution-Prediction Consistency Constraint (APC), which strengthens the alignment between fused features and emotion categories. Extensive experiments conducted on the IEMOCAP and MELD datasets have demonstrated the effectiveness of our proposed LSGMER model.

Hanyu Liu, Siyao Li, Ying Yu et al.

Human Activity Recognition (HAR) is a fundamental technology for numerous human - centered intelligent applications. Although deep learning methods have been utilized to accelerate feature extraction, issues such as multimodal data mixing, activity heterogeneity, and complex model deployment remain largely unresolved. The aim of this paper is to address issues such as multimodal data mixing, activity heterogeneity, and complex model deployment in sensor-based human activity recognition. We propose a spatiotemporal attention modal decomposition alignment fusion strategy to tackle the problem of the mixed distribution of sensor data. Key discriminative features of activities are captured through cross-modal spatio-temporal disentangled representation, and gradient modulation is combined to alleviate data heterogeneity. In addition, a wearable deployment simulation system is constructed. We conducted experiments on a large number of public datasets, demonstrating the effectiveness of the model.

Yinfeng Yu, Wenbing Huang, Fuchun Sun et al.

Audio-visual navigation task requires an agent to find a sound source in a realistic, unmapped 3D environment by utilizing egocentric audio-visual observations. Existing audio-visual navigation works assume a clean environment that solely contains the target sound, which, however, would not be suitable in most real-world applications due to the unexpected sound noise or intentional interference. In this work, we design an acoustically complex environment in which, besides the target sound, there exists a sound attacker playing a zero-sum game with the agent. More specifically, the attacker can move and change the volume and category of the sound to make the agent suffer from finding the sounding object while the agent tries to dodge the attack and navigate to the goal under the intervention. Under certain constraints to the attacker, we can improve the robustness of the agent towards unexpected sound attacks in audio-visual navigation. For better convergence, we develop a joint training mechanism by employing the property of a centralized critic with decentralized actors. Experiments on two real-world 3D scan datasets, Replica, and Matterport3D, verify the effectiveness and the robustness of the agent trained under our designed environment when transferred to the clean environment or the one containing sound attackers with random policy. Project: \url{https://yyf17.github.io/SAAVN}.