中文
相关论文

相关论文: PersonaGesture: Single-Reference Co-Speech Gesture…

200 篇论文

The generation of co-speech gestures for digital humans is an emerging area in the field of virtual human creation. Prior research has made progress by using acoustic and semantic information as input and adopting classify method to…

声音 · 计算机科学 2024-04-16 Fan Zhang , Naye Ji , Fuxing Gao , Siyuan Zhao , Zhaohan Wang , Shunman Li

Audio-driven one-shot talking face generation methods are usually trained on video resources of various persons. However, their created videos often suffer unnatural mouth shapes and asynchronous lips because those methods struggle to learn…

计算机视觉与模式识别 · 计算机科学 2021-12-07 Suzhen Wang , Lincheng Li , Yu Ding , Xin Yu

Recent breakthroughs in video AIGC have ushered in a transformative era for audio-driven human animation. However, conventional video dubbing techniques remain constrained to mouth region editing, resulting in discordant facial expressions…

计算机视觉与模式识别 · 计算机科学 2025-08-20 Shaoshu Yang , Zhe Kong , Feng Gao , Meng Cheng , Xiangyu Liu , Yong Zhang , Zhuoliang Kang , Wenhan Luo , Xunliang Cai , Ran He , Xiaoming Wei

We present a framework for generating full-bodied photorealistic avatars that gesture according to the conversational dynamics of a dyadic interaction. Given speech audio, we output multiple possibilities of gestural motion for an…

计算机视觉与模式识别 · 计算机科学 2024-01-04 Evonne Ng , Javier Romero , Timur Bagautdinov , Shaojie Bai , Trevor Darrell , Angjoo Kanazawa , Alexander Richard

Speech-driven 3D facial animation aims to synthesize realistic facial motion sequences from given audio, matching the speaker's speaking style. However, previous works often require priors such as class labels of a speaker or additional 3D…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Hyung Kyu Kim , Sangmin Lee , Hak Gu Kim

Recently, 2D speaking avatars have increasingly participated in everyday scenarios due to the fast development of facial animation techniques. However, most existing works neglect the explicit control of human bodies. In this paper, we…

计算机视觉与模式识别 · 计算机科学 2024-10-15 Jiazhi Guan , Quanwei Yang , Kaisiyuan Wang , Hang Zhou , Shengyi He , Zhiliang Xu , Haocheng Feng , Errui Ding , Jingdong Wang , Hongtao Xie , Youjian Zhao , Ziwei Liu

This paper presents a novel framework for automatic speech-driven gesture generation, applicable to human-agent interaction including both virtual agents and robots. Specifically, we extend recent deep-learning-based, data-driven methods…

人机交互 · 计算机科学 2019-06-12 Taras Kucherenko , Dai Hasegawa , Gustav Eje Henter , Naoshi Kaneko , Hedvig Kjellström

This paper introduces Motion Personalization, a new task that generates personalized motions aligned with text descriptions using several basic motions containing Persona. To support this novel task, we introduce a new large-scale motion…

计算机视觉与模式识别 · 计算机科学 2025-03-24 Boeun Kim , Hea In Jeong , JungHoon Sung , Yihua Cheng , Jeongmin Lee , Ju Yong Chang , Sang-Il Choi , Younggeun Choi , Saim Shin , Jungho Kim , Hyung Jin Chang

This paper proposes a novel automatic speech recognition (ASR) system that can transcribe individual speaker's speech while identifying whether they are target or non-target speakers from multi-talker overlapped speech. Target-speaker ASR…

Research in linguistics shows that non-verbal cues, such as gestures, play a crucial role in spoken discourse. For example, speakers perform hand gestures to indicate topic shifts, helping listeners identify transitions in discourse. In…

计算与语言 · 计算机科学 2025-03-06 Varsha Suresh , M. Hamza Mughal , Christian Theobalt , Vera Demberg

When virtual agents interact with humans, gestures are crucial to delivering their intentions with speech. Previous multimodal co-speech gesture generation models required encoded features of all modalities to generate gestures. If some…

计算机视觉与模式识别 · 计算机科学 2023-05-26 Gwantae Kim , Seonghyeok Noh , Insung Ham , Hanseok Ko

Isolating the voice of a specific person while filtering out other voices or background noises is challenging when video is shot in noisy environments. We propose audio-visual methods to isolate the voice of a single speaker and eliminate…

计算机视觉与模式识别 · 计算机科学 2018-02-13 Aviv Gabbay , Ariel Ephrat , Tavi Halperin , Shmuel Peleg

Most audio-visual speaker extraction methods rely on synchronized lip recording to isolate the speech of a target speaker from a multi-talker mixture. However, in natural human communication, co-speech gestures are also temporally aligned…

音频与语音处理 · 电气工程与系统科学 2026-01-28 Zexu Pan , Xinyuan Qian , Shengkui Zhao , Kun Zhou , Bin Ma

Personalised speech enhancement (PSE), which extracts only the speech of a target user and removes everything else from a recorded audio clip, can potentially improve users' experiences of audio AI modules deployed in the wild. To support a…

音频与语音处理 · 电气工程与系统科学 2022-11-09 Shucong Zhang , Malcolm Chadwick , Alberto Gil C. P. Ramos , Sourav Bhattacharya

Text-to-speech models trained on large-scale datasets have demonstrated impressive in-context learning capabilities and naturalness. However, control of speaker identity and style in these models typically requires conditioning on reference…

声音 · 计算机科学 2024-02-08 Dan Lyth , Simon King

We present a multimodal learning-based method to simultaneously synthesize co-speech facial expressions and upper-body gestures for digital characters using RGB video data captured using commodity cameras. Our approach learns from sparse…

计算机视觉与模式识别 · 计算机科学 2024-11-26 Uttaran Bhattacharya , Aniket Bera , Dinesh Manocha

Diffusion models can synthesize realistic co-speech video from audio for various applications, such as video creation and virtual agents. However, existing diffusion-based methods are slow due to numerous denoising steps and costly…

计算机视觉与模式识别 · 计算机科学 2025-10-06 Beijia Lu , Ziyi Chen , Jing Xiao , Jun-Yan Zhu

Body language such as conversational gesture is a powerful way to ease communication. Conversational gestures do not only make a speech more lively but also contain semantic meaning that helps to stress important information in the…

机器人学 · 计算机科学 2022-10-14 Hitoshi Teshima , Naoki Wake , Diego Thomas , Yuta Nakashima , Hiroshi Kawasaki , Katsushi Ikeuchi

We present a cross-modal unsupervised framework for active speaker detection in media content such as TV shows and movies. Machine learning advances have enabled impressive performance in identifying individuals from speech and facial…

图像与视频处理 · 电气工程与系统科学 2022-09-27 Rahul Sharma , Shrikanth Narayanan

Lip-to-Speech (Lip2Speech) synthesis, which predicts corresponding speech from talking face images, has witnessed significant progress with various models and training strategies in a series of independent studies. However, existing studies…

多媒体 · 计算机科学 2023-05-25 Zheng-Yan Sheng , Yang Ai , Zhen-Hua Ling