English
Related papers

Related papers: V2A-Mapper: A Lightweight Solution for Vision-to-A…

200 papers

Video-to-Audio (V2A) generation requires balancing four critical perceptual dimensions: semantic consistency, audio-visual temporal synchrony, aesthetic quality, and spatial accuracy; yet existing methods suffer from objective entanglement…

Sound · Computer Science 2026-03-04 Huadai Liu , Kaicheng Luo , Wen Wang , Qian Chen , Peiwen Sun , Rongjie Huang , Xiangang Li , Jieping Ye , Wei Xue

Recent studies show that pretrained vision models can boost performance in audio downstream tasks. To enhance the performance further, an additional pretraining stage with large scale audio data is typically required to infuse audio…

Sound · Computer Science 2024-12-10 Juan Yeo , Jinkwan Jang , Kyubyung Chae , Seongkyu Mun , Taesup Kim

Although audio generation shares commonalities across different types of audio, such as speech, music, and sound effects, designing models for each type requires careful consideration of specific objectives and biases that can significantly…

While vision-language pretrained models (VLMs) excel in various multimodal understanding tasks, their potential in fine-grained audio-visual reasoning, particularly for audio-visual question answering (AVQA), remains largely unexplored.…

Computer Vision and Pattern Recognition · Computer Science 2024-05-14 Yuanyuan Jiang , Jianqin Yin

Articulatory-to-acoustic (A2A) synthesis refers to the generation of audible speech from captured movement of the speech articulators. This technique has numerous applications, such as restoring oral communication to people who cannot…

Contrastive language-audio pre-training (CLAP), which learns audio-language representations by aligning audio and text in a common feature space, has become popular for solving audio tasks. However, CLAP's audio features lack…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-16 Daisuke Niizumi , Daiki Takeuchi , Masahiro Yasuda , Binh Thien Nguyen , Yasunori Ohishi , Noboru Harada

Recently, the application of diffusion models has facilitated the significant development of speech and audio generation. Nevertheless, the quality of samples generated by diffusion models still needs improvement. And the effectiveness of…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-13 Wenhao Guan , Kaidi Wang , Wangjin Zhou , Yang Wang , Feng Deng , Hui Wang , Lin Li , Qingyang Hong , Yong Qin

Generating high-quality and temporally synchronized audio from video content is essential for video editing and post-production tasks, enabling the creation of semantically aligned audio for silent videos. However, most existing approaches…

Sound · Computer Science 2025-08-18 Haomin Zhang , Kristin Qi , Shuxin Yang , Zihao Chen , Chaofan Ding , Xinhan Di

Recent advances in multimodal large language models (MLLMs) have enabled impressive progress in vision-language understanding, yet their high computational cost limits deployment in resource-constrained scenarios such as robotic…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Quoc-Huy Trinh

The increasing success of audio foundation models across various tasks has led to a growing need for improved interpretability to understand their intricate decision-making processes better. Existing methods primarily focus on explaining…

Sound · Computer Science 2024-10-11 Alican Akman , Qiyang Sun , Björn W. Schuller

How does audio describe the world around us? In this paper, we propose a method for generating an image of a scene from sound. Our method addresses the challenges of dealing with the large gaps that often exist between sight and sound. We…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 Kim Sung-Bin , Arda Senocak , Hyunwoo Ha , Andrew Owens , Tae-Hyun Oh

Large-scale pretrained foundation models have been an emerging paradigm for building artificial intelligence (AI) systems, which can be quickly adapted to a wide range of downstream tasks. This paper presents mPLUG, a new vision-language…

Computation and Language · Computer Science 2023-07-06 Chenliang Li , Haiyang Xu , Junfeng Tian , Wei Wang , Ming Yan , Bin Bi , Jiabo Ye , Hehong Chen , Guohai Xu , Zheng Cao , Ji Zhang , Songfang Huang , Fei Huang , Jingren Zhou , Luo Si

We propose Im2Wav, an image guided open-domain audio generation system. Given an input image or a sequence of images, Im2Wav generates a semantically relevant sound. Im2Wav is based on two Transformer language models, that operate over a…

Sound · Computer Science 2023-02-28 Roy Sheffer , Yossi Adi

Employing LLMs for visual generation has recently become a research focus. However, the existing methods primarily transfer the LLM architecture to visual generation but rarely investigate the fundamental differences between language and…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Teng Hu , Jiangning Zhang , Ran Yi , Jieyu Weng , Yabiao Wang , Xianfang Zeng , Zhucun Xue , Lizhuang Ma

We introduce MMAudioSep, a generative model for video/text-queried sound separation that is founded on a pretrained video-to-audio model. By leveraging knowledge about the relationship between video/text and audio learned through a…

Sound · Computer Science 2026-04-20 Akira Takahashi , Shusuke Takahashi , Yuki Mitsufuji

Vision-Language Models (VLMs), such as CLIP, exhibit strong image-text comprehension abilities, facilitating advances in several downstream tasks such as zero-shot image classification, image-text retrieval, and text-to-image generation.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-26 Le Zhang , Rabiul Awal , Aishwarya Agrawal

Given a query from one modality, few-shot cross-modal retrieval (CMR) retrieves semantically similar instances in another modality with the target domain including classes that are disjoint from the source domain. Compared with classical…

Computer Vision and Pattern Recognition · Computer Science 2024-11-27 Jingyou Xie , Jiayi Kuang , Zhenzhou Lin , Jiarui Ouyang , Zishuo Zhao , Ying Shen

Foundation models like CLIP and SAM have advanced computer vision and medical imaging via low-shot transfer learning, aiding CADD with limited data. However, their deployment faces two key challenges. \textit{distribution shift} where…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Behraj Khan , Tahir Qasim Syed , Nouman M. Durrani , Bilal Naseem , Shabir Ahmad , Rizwan Qureshi

Generating music that temporally aligns with video events is challenging for existing text-to-music models, which lack fine-grained temporal control. We introduce V2M-ZERO, a video-to-music generation approach that generates time-aligned…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Yan-Bo Lin , Jonah Casebeer , Long Mai , Aniruddha Mahapatra , Gedas Bertasius , Nicholas J. Bryan

We present MGAudio, a novel flow-based framework for open-domain video-to-audio generation, which introduces model-guided dual-role alignment as a central design principle. Unlike prior approaches that rely on classifier-based or…

Sound · Computer Science 2025-10-29 Kang Zhang , Trung X. Pham , Suyeon Lee , Axi Niu , Arda Senocak , Joon Son Chung