paper-with-me

Papers

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

2025-04-08 · Tianshui Chen, Jianman Lin, Zhijing Yang, Chumei Qing, Yukai Shi, Liang Lin

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.

📄 PDF Abstract BibTeX arXiv:2504.05672

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningRepresentation Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Regularizing Contrastive Predictive Coding for Speech Applications

2023-04-12 · Saurabhchand Bhati, Jesús Villalba, Piotr Żelasko, Laureano Moro-Velazquez 외

Self-supervised methods such as Contrastive predictive Coding (CPC) have greatly improved the quality of the unsupervised representations. These representations significantly reduce the amount of labeled data needed for …

Acoustic Unit DiscoveryAutomatic Speech RecognitionData Augmentationspeech-recognition+1

Joint-Centric Dual Contrastive Alignment with Structure-Preserving and Information-Balanced Regularization

2026-04-17 · Habibeh Naderi, Behrouz Haji Soleimani, Stan Matwin arxiv

We propose HILBERT (HIerarchical Long-sequence Balanced Embedding with Reciprocal contrastive Training), a cross-attentive multimodal framework for learning document-level audio-text representations from long, segmented …

i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning

2020-10-17 · ICLR 2021 1 · Kibok Lee, Yian Zhu, Kihyuk Sohn, Chun-Liang Li 외

Contrastive representation learning has shown to be effective to learn representations from unlabeled data. However, much progress has been made in vision domains relying on data augmentations carefully designed using do…

Contrastive LearningRepresentation Learning

All Information is Necessary: Integrating Speech Positive and Negative Information by Contrastive Learning for Speech Enhancement

2023-04-26 · Xinmeng Xu, Weiping tu, Chang Han, Yuhong Yang

Monaural speech enhancement (SE) is an ill-posed problem due to the irreversible degradation process. Recent methods to achieve SE tasks rely solely on positive information, e.g., ground-truth speech and speech-relevant …

AllContrastive LearningSpeech Enhancement

Contrastive Regularization for Accent-Robust ASR

2026-05-05 · Van-Phat Thai, Aradhya Dhruv, Duc-Thinh Pham, Sameer Alam arxiv

ASR systems based on self-supervised acoustic pretraining and CTC fine-tuning achieve strong performance on native speech but remain sensitive to accent variability. We investigate supervised contrastive learning (SupCon…

Contrastive Learning