Contrastive Decoupled Representation Learning and Regularization for Speech-Preserving Facial Expression Manipulation

• URL: http://arxiv.org/abs/2504.05672v1
• Date: Tue, 08 Apr 2025 04:34:38 GMT
• Title: Contrastive Decoupled Representation Learning and Regularization for Speech-Preserving Facial Expression Manipulation
• Authors: Tianshui Chen, Jianman Lin, Zhijing Yang, Chumei Qing, Yukai Shi, Liang Lin,
• Abstract summary: Speech-preserving facial expression manipulation (SPFEM) aims to modify a talking head to display a specific reference emotion.<n>Emotion and content information existing in reference and source inputs can provide direct and accurate supervision signals for SPFEM models.<n>We propose to learn content and emotion priors as guidance augmented with contrastive learning to learn decoupled content and emotion representation.
• Score: 58.189703277322224
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Speech-preserving facial expression manipulation (SPFEM) aims to modify a talking head to display a specific reference emotion while preserving the mouth animation of source spoken contents. Thus, emotion and content information existing in reference and source inputs can provide direct and accurate supervision signals for SPFEM models. However, the intrinsic intertwining of these elements during the talking process poses challenges to their effectiveness as supervisory signals. In this work, we propose to learn content and emotion priors as guidance augmented with contrastive learning to learn decoupled content and emotion representation via an innovative Contrastive Decoupled Representation Learning (CDRL) algorithm. Specifically, a Contrastive Content Representation Learning (CCRL) module is designed to learn audio feature, which primarily contains content information, as content priors to guide learning content representation from the source input. Meanwhile, a Contrastive Emotion Representation Learning (CERL) module is proposed to make use of a pre-trained visual-language model to learn emotion prior, which is then used to guide learning emotion representation from the reference input. We further introduce emotion-aware and emotion-augmented contrastive learning to train CCRL and CERL modules, respectively, ensuring learning emotion-independent content representation and content-independent emotion representation. During SPFEM model training, the decoupled content and emotion representations are used to supervise the generation process, ensuring more accurate emotion manipulation together with audio-lip synchronization. Extensive experiments and evaluations on various benchmarks show the effectiveness of the proposed algorithm.

Related papers

• EmoSEM: Segment and Explain Emotion Stimuli in Visual Art [25.539022846134543]
  This paper focuses on a key challenge in visual art understanding: given an art image, the model pinpoints pixel regions that trigger a specific human emotion. Despite recent advances in art understanding, pixel-level emotion understanding still faces a dual challenge. This paper proposes the Emotion stimuli and Explanation Model (EmoSEM) to endow the segmentation model SAM with emotion comprehension capability.
  arXiv  Detail & Related papers  (2025-04-20T15:40:00Z)
• EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning [26.95442405140093]
  We focus on enhancing the model's proficiency in understanding and adhering to instructions related to emotional contexts. We introduce a novel GPT-assisted pipeline for generating emotion visual instruction data. Our proposed EmoVIT architecture incorporates emotion-specific instruction data, leveraging the powerful capabilities of Large Language Models.
  arXiv  Detail & Related papers  (2024-04-25T15:15:36Z)
• Multimodal Emotion Recognition by Fusing Video Semantic in MOOC Learning Scenarios [6.987099464814016]
  In Massive Open Online Courses (MOOC), semantic information of instructional videos has a crucial impact on learners' emotional state. This paper proposes a multimodal emotion recognition method by fusing video semantic information and semantic signals. The experimental results show that our method has significantly improved emotion recognition performance.
  arXiv  Detail & Related papers  (2024-04-11T05:44:27Z)
• VLLMs Provide Better Context for Emotion Understanding Through Common Sense Reasoning [66.23296689828152]
  We leverage the capabilities of Vision-and-Large-Language Models to enhance in-context emotion classification. In the first stage, we propose prompting VLLMs to generate descriptions in natural language of the subject's apparent emotion. In the second stage, the descriptions are used as contextual information and, along with the image input, are used to train a transformer-based architecture.
  arXiv  Detail & Related papers  (2024-04-10T15:09:15Z)
• Attention-based Interactive Disentangling Network for Instance-level Emotional Voice Conversion [81.1492897350032]
  Emotional Voice Conversion aims to manipulate a speech according to a given emotion while preserving non-emotion components. We propose an Attention-based Interactive diseNtangling Network (AINN) that leverages instance-wise emotional knowledge for voice conversion.
  arXiv  Detail & Related papers  (2023-12-29T08:06:45Z)
• Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling [50.99252242917458]
  Conversational Speech Synthesis (CSS) aims to accurately express an utterance with the appropriate prosody and emotional inflection within a conversational setting. To address the issue of data scarcity, we meticulously create emotional labels in terms of category and intensity. Our model outperforms the baseline models in understanding and rendering emotions.
  arXiv  Detail & Related papers  (2023-12-19T08:47:50Z)
• Exploring Emotion Expression Recognition in Older Adults Interacting with a Virtual Coach [22.00225071959289]
  EMPATHIC project aimed to design an emotionally expressive virtual coach capable of engaging healthy seniors to improve well-being and promote independent aging. This paper outlines the development of the emotion expression recognition module of the virtual coach, encompassing data collection, annotation design, and a first methodological approach.
  arXiv  Detail & Related papers  (2023-11-09T18:22:32Z)
• StyleEDL: Style-Guided High-order Attention Network for Image Emotion Distribution Learning [69.06749934902464]
  We propose a style-guided high-order attention network for image emotion distribution learning termed StyleEDL. StyleEDL interactively learns stylistic-aware representations of images by exploring the hierarchical stylistic information of visual contents. In addition, we introduce a stylistic graph convolutional network to dynamically generate the content-dependent emotion representations.
  arXiv  Detail & Related papers  (2023-08-06T03:22:46Z)
• Learning Emotion Representations from Verbal and Nonverbal Communication [7.747924294389427]
  We present EmotionCLIP, the first pre-training paradigm to extract visual emotion representations from verbal and nonverbal communication. We guide EmotionCLIP to attend to nonverbal emotion cues through subject-aware context encoding and verbal emotion cues using sentiment-guided contrastive learning. EmotionCLIP will address the prevailing issue of data scarcity in emotion understanding, thereby fostering progress in related domains.
  arXiv  Detail & Related papers  (2023-05-22T21:36:55Z)
• An Attribute-Aligned Strategy for Learning Speech Representation [57.891727280493015]
  We propose an attribute-aligned learning strategy to derive speech representation that can flexibly address these issues by attribute-selection mechanism. Specifically, we propose a layered-representation variational autoencoder (LR-VAE), which factorizes speech representation into attribute-sensitive nodes. Our proposed method achieves competitive performances on identity-free SER and a better performance on emotionless SV.
  arXiv  Detail & Related papers  (2021-06-05T06:19:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.