中文
相关论文

相关论文: DeepAudio-V1:Towards Multi-Modal Multi-Stage End-t…

200 篇论文

Video-to-Audio (V2A) generation is essential for immersive multimedia experiences, yet its evaluation remains underexplored. Existing benchmarks typically assess diverse audio types under a unified protocol, overlooking the fine-grained…

声音 · 计算机科学 2026-04-14 Qian Zhang , Yuqin Cao , Yixuan Gao , Xiongkuo Min

Despite progress in video-to-audio generation, the field focuses predominantly on mono output, lacking spatial immersion. Existing binaural approaches remain constrained by a two-stage pipeline that first generates mono audio and then…

计算机视觉与模式识别 · 计算机科学 2025-12-03 Mengchen Zhang , Qi Chen , Tong Wu , Zihan Liu , Dahua Lin

Training a unified model integrating video-to-audio (V2A), text-to-audio (T2A), and joint video-text-to-audio (VT2A) generation offers significant application flexibility, yet faces two unexplored foundational challenges: (1) the scarcity…

声音 · 计算机科学 2026-04-30 Yusheng Dai , Zehua Chen , Yuxuan Jiang , Baolong Gao , Qiuhong Ke , Jianfei Cai , Jun Zhu

Currently, high-quality, synchronized audio is synthesized from video and optional text inputs using various multi-modal joint learning frameworks. However, the precise alignment between the visual and generated audio domains remains far…

声音 · 计算机科学 2025-03-31 Yunming Liang , Zihao Chen , Chaofan Ding , Xinhan Di

While video-to-audio generation has achieved remarkable progress in semantic and temporal alignment, most existing studies focus solely on these aspects, paying limited attention to the spatial perception and immersive quality of the…

计算机视觉与模式识别 · 计算机科学 2026-01-30 Yanan Wang , Linjie Ren , Zihao Li , Junyi Wang , Tian Gan

Video-to-audio (V2A) generation aims to synthesize realistic and semantically aligned audio from silent videos, with potential applications in video editing, Foley sound design, and assistive multimedia. Although the excellent results,…

While recent video-to-audio (V2A) models can generate realistic background audio from visual input, they largely overlook speech, an essential part of many video soundtracks. This paper proposes a new task, video-to-soundtrack (V2ST)…

多媒体 · 计算机科学 2025-07-15 Wenjie Tian , Xinfa Zhu , Haohe Liu , Zhixian Zhao , Zihao Chen , Chaofan Ding , Xinhan Di , Junjie Zheng , Lei Xie

Recent advances in audio generation have focused on text-to-audio (T2A) and video-to-audio (V2A) tasks. However, T2A or V2A methods cannot generate holistic sounds (onscreen and off-screen). This is because T2A cannot generate sounds…

计算机视觉与模式识别 · 计算机科学 2024-12-17 Saksham Singh Kushwaha , Yapeng Tian

Video-to-audio (V2A) generation leverages visual-only video features to render plausible sounds that match the scene. Importantly, the generated sound onsets should match the visual actions that are aligned with them, otherwise unnatural…

声音 · 计算机科学 2024-07-16 Santiago Pascual , Chunghsin Yeh , Ioannis Tsiamas , Joan Serrà

Visual and auditory perception are two crucial ways humans experience the world. Text-to-video generation has made remarkable progress over the past year, but the absence of harmonious audio in generated video limits its broader…

声音 · 计算机科学 2025-03-25 Yong Ren , Chenxing Li , Manjie Xu , Wei Liang , Yu Gu , Rilin Chen , Dong Yu

We propose to synthesize high-quality and synchronized audio, given video and optional text conditions, using a novel multimodal joint training framework MMAudio. In contrast to single-modality training conditioned on (limited) video data…

计算机视觉与模式识别 · 计算机科学 2025-04-09 Ho Kei Cheng , Masato Ishii , Akio Hayakawa , Takashi Shibuya , Alexander Schwing , Yuki Mitsufuji

In recent times, the focus on text-to-audio (TTA) generation has intensified, as researchers strive to synthesize audio from textual descriptions. However, most existing methods, though leveraging latent diffusion models to learn the…

声音 · 计算机科学 2024-03-14 Shentong Mo , Jing Shi , Yapeng Tian

Current video-to-audio (V2A) methods struggle in complex multi-event scenarios (video scenarios involving multiple sound sources, sound events, or transitions) due to two critical limitations. First, existing methods face challenges in…

多媒体 · 计算机科学 2025-11-05 Jianxuan Yang , Xiaoran Yang , Lipan Zhang , Xinyue Guo , Zhao Wang , Gongping Huang

Recent advances in video generation have been remarkable, enabling models to produce visually compelling videos with synchronized audio. While existing video generation benchmarks provide comprehensive metrics for visual quality, they lack…

计算机视觉与模式识别 · 计算机科学 2026-04-07 Daili Hua , Xizhi Wang , Bohan Zeng , Xinyi Huang , Hao Liang , Junbo Niu , Xinlong Chen , Quanqing Xu , Wentao Zhang

Current movie dubbing technology can produce the desired speech using a reference voice and input video, maintaining perfect synchronization with the visuals while effectively conveying the intended emotions. However, crucial aspects of…

多媒体 · 计算机科学 2025-05-23 Junjie Zheng , Zihao Chen , Chaofan Ding , Yunming Liang , Yihan Fan , Huan Yang , Lei Xie , Xinhan Di

Video-to-audio (V2A) generation is important for video editing and post-processing, enabling the creation of semantics-aligned audio for silent video. However, most existing methods focus on generating short-form audio for short video…

声音 · 计算机科学 2024-12-31 Xin Cheng , Xihua Wang , Yihan Wu , Yuyue Wang , Ruihua Song

Video-to-audio (V2A) generation aims to produce corresponding audio given silent video inputs. This task is particularly challenging due to the cross-modality and sequential nature of the audio-visual features involved. Recent works have…

声音 · 计算机科学 2024-09-17 Mingjing Yi , Ming Li

The generation of realistic, context-aware audio is important in real-world applications such as video game development. While existing video-to-audio (V2A) methods mainly focus on Foley sound generation, they struggle to produce…

We present \textsc{Vx2Text}, a framework for text generation from multimodal inputs consisting of video plus text, speech, or audio. In order to leverage transformer networks, which have been shown to be effective at modeling language, each…

计算机视觉与模式识别 · 计算机科学 2021-02-02 Xudong Lin , Gedas Bertasius , Jue Wang , Shih-Fu Chang , Devi Parikh , Lorenzo Torresani

As artificial intelligence-generated content (AIGC) continues to evolve, video-to-audio (V2A) generation has emerged as a key area with promising applications in multimedia editing, augmented reality, and automated content creation. While…

计算机视觉与模式识别 · 计算机科学 2025-03-17 Yuhuan You , Xihong Wu , Tianshu Qu
‹ 上一页 1 2 3 10 下一页 ›