LYLei Yang

Lei Yang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Lei Yang has a total of 14 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Landmark Guided Visual Feature Extractor for Visual Speech Recognition with Limited Resource

    by Lei Yang, Junshan Jin, Mingyuan Zhang, Yi He, Bofan Chen, Shi-Lin Wang

  • Open Access

    Enhancing Visual Forced Alignment with Local Context-Aware Feature Extraction and Multi-Task Learning

    by Yi He, Lei Yang, Shilin Wang

    This paper introduces a novel approach to Visual Forced Alignment (VFA), aiming to accurately synchronize utterances with corresponding lip movements, without relying on audio cues. We propose a novel VFA approach that integrates a local context-aware feature extractor and employs multi-task learning to refine both global and local context features, enhancing sensitivity to subtle lip movements for precise word-level and phoneme-level alignment. Incorporating the improved Viterbi algorithm for post-processing, our method significantly reduces misalignments. Experimental results show our approach outperforms existing methods, achieving a 6% accuracy improvement at the word-level and 27% improvement at the phoneme-level in LRS2 dataset. These improvements offer new potential for applications in automatically subtitling TV shows or user-generated content platforms like TikTok and YouTube Shorts.

  • Open Access

    Acupuncture for rehabilitation after total knee arthroplasty: a systematic review and network meta-analysis

    by Wen-Xuan Li, Cai-Qin Wu, Wei Feng, Yi-Jun Zhan, Lei Yang, Heng-Jie Jia, Jian Pei, Kun-Peng Li

    Background: The increasing interest in acupuncture for promoting postoperative rehabilitation has encouraged its use in rehabilitation after total knee arthroplasty (TKA), but its effectiveness remains controversial. Objective: This study aims to assess the efficacy of different models of acupuncture-related therapies on pain relief, motor function, inflammation, and overall rehabilitation of the knee after TKA. Methods: Databases PubMed, Embase, Cochrane, Web of Science, Scopus, and Clinicaltrials.gov were searched to screen eligible randomized controlled trials (RCTs). All RCTs that used acupuncture/moxibustion on TKA patients were included by two researchers independently after rigorous quality evaluation, with data extracted. The statistics were performed by using R 4.2.3 and Stata 17. Results: The network meta-analysis incorporated 28 RCTs, 21 of which were conducted in mainland China and Taiwan. Evidence of the relation of several common acupuncture/moxibustion treatments was shown by the network meta-analysis (NMA). The results of NMA showed that electroacupuncture was the preferred therapy for soothing pain symptoms (standardized mean difference=0.58, 95% CI=0.36–0.81). Auricular acupressure was the best treatment to improve the knee motor function. Electroacupuncture was superior to special acupuncture in relieving knee joint stiffness and inflammation. Conclusion: Acupuncture intervention, especially electroacupuncture, can effectively alleviate pain, improve motion, reduce stiffness, and decrease inflammation in post-TKA patients with no serious adverse events.


  • Lip Feature Disentanglement for Visual Speaker Authentication in Natural Scenes

    by Yi He, Lei Yang, Shilin Wang, Alan Wee-Chung Liew

    Recent studies have shown that lip shape and movement can be used as an effective biometric feature for speaker authentication. By using random prompt text scheme, lip-based authentication system can also achieve good liveness detection performance in laboratory scenarios. However, due to the increasingly widespread mobile application, the authentication system may face additional practical difficulties such as complex background, limited user samples, etc., which will degrade the authentication performance derived by current methods. To confront the above problems, a new deep neural network, i.e. the Triple-feature Disentanglement Network for Visual Speaker Authentication (TDVSA-Net), is proposed in this paper to extract discriminative and disentangled lip features for visual speaker authentication in the random prompt text scenario. Three decoupled lip features, including the content feature inferring the speech content, the physiological lip feature describing the static lip shape and appearance and the behavioral lip feature depicting the unique pattern in lip movements during utterance, are extracted by TDVSA-Net and fed into corresponding modules to authenticate both the prompt text and the speaker’s identity. Experiment results have demonstrated that compared with several SOTA visual speaker authentication methods, the proposed TDVSA-Net can extract more discriminative and robust lip features which boost the content recognition and identity authentication performance against both human imposters and DeepFake attacks.


  • Fine-Grained Lip Image Segmentation Using Fuzzy Logic and Graph Reasoning

    by Lei Yang, Shilin Wang, Alan Wee-Chung Liew

    Fine-grained lip image segmentation plays a critical role in downstream tasks such as automatic lipreading, as it enables the accurate identification of inner mouth components such as teeth and tongue which are essential for comprehending spoken utterances. However, achieving accurate and robust lip image segmentation in natural scenes is still challenging due to significant variations in lighting condition, head pose and background. This paper proposes a novel deep neural network based method for fine-grained lip image segmentation that exploits fuzzy and graph theories to handle these variations. A fuzzy learning module is designed to deal with the uncertainties in color and edge information and enhance feature maps at various scales. The fuzzy graph reasoning module with fuzzy projection models the relationship among semantics components and achieves a global receptive field. In our experiments, a fine-grained lip region segmentation dataset, i.e., FLRSeg, is built for evaluation and experiment results have shown that the proposed method can achieve superior segmentation performance (94.36% in pixel accuracy and 74.89% in mIoU) compared with several SOTA lip image segmentation methods.