中文
相关论文

相关论文: LES-Talker: Fine-Grained Emotion Editing for Talki…

200 篇论文

Speech-driven 3D face animation aims to generate realistic facial expressions that match the speech content and emotion. However, existing methods often neglect emotional facial expressions or fail to disentangle them from speech content.…

计算机视觉与模式识别 · 计算机科学 2023-08-28 Ziqiao Peng , Haoyu Wu , Zhenbo Song , Hao Xu , Xiangyu Zhu , Jun He , Hongyan Liu , Zhaoxin Fan

Several works have developed end-to-end pipelines for generating lip-synced talking faces with various real-world applications, such as teaching and language translation in videos. However, these prior works fail to create realistic-looking…

计算机视觉与模式识别 · 计算机科学 2023-03-28 Sahil Goyal , Shagun Uppal , Sarthak Bhagat , Yi Yu , Yifang Yin , Rajiv Ratn Shah

Recent advances in text-to-speech (TTS) have enabled models to clone arbitrary unseen speakers and synthesize high-quality, natural-sounding speech. However, evaluation methods lag behind: typical mean opinion score (MOS) estimators perform…

音频与语音处理 · 电气工程与系统科学 2025-11-25 Guansu Wang , Peijie Sun

Text-based speech editing allows users to edit speech by intuitively cutting, copying, and pasting text to speed up the process of editing speech. In the previous work, CampNet (context-aware mask prediction network) is proposed to realize…

声音 · 计算机科学 2022-12-21 Tao Wang , Jiangyan Yi , Ruibo Fu , Jianhua Tao , Zhengqi Wen , Chu Yuan Zhang

While the recent advances in research on video reenactment have yielded promising results, the approaches fall short in capturing the fine, detailed, and expressive facial features (e.g., lip-pressing, mouth puckering, mouth gaping, and…

计算机视觉与模式识别 · 计算机科学 2023-02-15 Trevine Oorloff , Yaser Yacoob

Audio-driven talking-head synthesis is a popular research topic for virtual human-related applications. However, the inflexibility and inefficiency of existing methods, which necessitate expensive end-to-end training to transfer emotions…

声音 · 计算机科学 2023-10-13 Yuan Gan , Zongxin Yang , Xihang Yue , Lingyun Sun , Yi Yang

Generative Adversarial Network approaches such as StyleGAN/2 provide two key benefits: the ability to generate photo-realistic face images and possessing a semantically structured latent space from which these images are created. Many…

计算机视觉与模式识别 · 计算机科学 2025-05-13 Jingrui He , Andrew Stephen McGough

Emotional talking head generation has attracted growing attention. Previous methods, which are mainly GAN-based, still struggle to consistently produce satisfactory results across diverse emotions and cannot conveniently specify…

计算机视觉与模式识别 · 计算机科学 2024-08-13 Yifeng Ma , Shiwei Zhang , Jiayu Wang , Xiang Wang , Yingya Zhang , Zhidong Deng

Generating emotion-specific talking head videos from audio input is an important and complex challenge for human-machine interaction. However, emotion is highly abstract concept with ambiguous boundaries, and it necessitates disentangled…

计算机视觉与模式识别 · 计算机科学 2025-04-03 Xuli Shen , Hua Cai , Dingding Yu , Weilin Shen , Qing Xu , Xiangyang Xue

Achieving disentangled control over multiple facial motions and accommodating diverse input modalities greatly enhances the application and entertainment of the talking head generation. This necessitates a deep exploration of the decoupling…

计算机视觉与模式识别 · 计算机科学 2024-04-03 Shuai Tan , Bin Ji , Mengxiao Bi , Ye Pan

Speech emotion recognition is the task of recognizing the speaker's emotional state given a recording of their utterance. While most of the current approaches focus on inferring emotion from isolated utterances, we argue that this is not…

计算与语言 · 计算机科学 2021-09-14 Raghavendra Pappagari , Piotr Żelasko , Jesús Villalba , Laureano Moro-Velazquez , Najim Dehak

Affect is often expressed via non-verbal body language such as actions/gestures, which are vital indicators for human behaviors. Recent studies on recognition of fine-grained actions/gestures in monocular images have mainly focused on…

计算机视觉与模式识别 · 计算机科学 2021-01-19 Ardhendu Behera , Zachary Wharton , Morteza Ghahremani , Swagat Kumar , Nik Bessis

We propose StyleTalker, a novel audio-driven talking head generation model that can synthesize a video of a talking person from a single reference image with accurately audio-synced lip shapes, realistic head poses, and eye blinks.…

计算机视觉与模式识别 · 计算机科学 2024-03-18 Dongchan Min , Minyoung Song , Eunji Ko , Sung Ju Hwang

Multimodal emotion analysis is shifting from static classification to generative reasoning. Beyond simple label prediction, robust affective reasoning must synthesize fine-grained signals such as facial micro-expressions and prosodic which…

多媒体 · 计算机科学 2026-02-05 Zhixian Zhao , Wenjie Tian , Lei Xie

Affective computing and cognitive theory are widely used in modern human-computer interaction scenarios. Human faces, as the most prominent and easily accessible features, have attracted great attention from researchers. Since humans have…

计算机视觉与模式识别 · 计算机科学 2020-01-20 Wenxuan Wang , Yanwei Fu , Qiang Sun , Tao Chen , Chenjie Cao , Ziqi Zheng , Guoqiang Xu , Han Qiu , Yu-Gang Jiang , Xiangyang Xue

Large language models (LLMs) have demonstrated impressive performance in mathematical and commonsense reasoning tasks using chain-of-thought (CoT) prompting techniques. But can they perform emotional reasoning by concatenating `Let's think…

计算与语言 · 计算机科学 2024-08-12 Ankita Bhaumik , Tomek Strzalkowski

Purpose: Emotion is a fundamental component of human communication, shaping understanding, trust, and engagement across domains such as education, healthcare, and mental health. While large language models (LLMs) exhibit strong reasoning…

计算与语言 · 计算机科学 2025-10-15 Yurui Dong , Luozhijie Jin , Yao Yang , Bingjie Lu , Jiaxi Yang , Zhi Liu

Speech-driven 3D talking head generation aims to produce lifelike facial animations precisely synchronized with speech. While considerable progress has been made in achieving high lip-synchronization accuracy, existing methods largely…

计算机视觉与模式识别 · 计算机科学 2025-12-30 Bin Wang , Yang Xu , Huan Zhao , Hao Zhang , Zixing Zhang

While current emotional Text-to-Speech (TTS) models have successfully controlled verbal prosody, they often ignore non-verbal vocalizations (NVs), which are essential for authentic human emotion. Although some non-verbal datasets have…

音频与语音处理 · 电气工程与系统科学 2026-05-26 Wangzixi Zhou , Bagus Tris Atmaja , Sakriani Sakti

Multimodal-driven talking face generation refers to animating a portrait with the given pose, expression, and gaze transferred from the driving image and video, or estimated from the text and audio. However, existing methods ignore the…

计算机视觉与模式识别 · 计算机科学 2023-05-10 Chao Xu , Shaoting Zhu , Junwei Zhu , Tianxin Huang , Jiangning Zhang , Ying Tai , Yong Liu