English
Related papers

Related papers: MeanFlow-Accelerated Multimodal Video-to-Audio Syn…

200 papers

Recent hybrid video generation models combine autoregressive temporal dynamics with diffusion-based spatial denoising, but their sequential, iterative nature leads to error accumulation and long inference times. In this work, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Yongqi Yang , Huayang Huang , Xu Peng , Xiaobin Hu , Donghao Luo , Jiangning Zhang , Chengjie Wang , Yu Wu

As text-to-speech technologies achieve remarkable naturalness in read-aloud tasks, there is growing interest in multimodal synthesis of verbal and non-verbal communicative behaviour, such as spontaneous speech and associated body gestures.…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-11 Shivam Mehta , Ruibo Tu , Simon Alexanderson , Jonas Beskow , Éva Székely , Gustav Eje Henter

Flow matching offers a robust and stable approach to training diffusion models. However, directly applying flow matching to neural vocoders can result in subpar audio quality. In this work, we present WaveFM, a reparameterized flow matching…

Sound · Computer Science 2025-03-24 Tianze Luo , Xingchen Miao , Wenbo Duan

Conditional Flow Matching (CFM), a simulation-free method for training continuous normalizing flows, provides an efficient alternative to diffusion models for key tasks like image and video generation. The performance of CFM in solving…

Machine Learning · Computer Science 2026-03-17 Aram Davtyan , Leello Tadesse Dadi , Volkan Cevher , Paolo Favaro

Video diffusion generation suffers from critical sampling efficiency bottlenecks, particularly for large-scale models and long contexts. Existing video acceleration methods, adapted from image-based techniques, lack a single-step…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Jiaxiang Cheng , Bing Ma , Xuhua Ren , Hongyi Henry Jin , Kai Yu , Peng Zhang , Wenyue Li , Yuan Zhou , Tianxiang Zheng , Qinglin Lu

Diffusion- and flow-based models have advanced Real-world Image Super-Resolution (Real-ISR), but their multi-step sampling makes inference slow and hard to deploy. One-step distillation alleviates the cost, yet often degrades restoration…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Ruiqing Wang , Kai Zhang , Yuanzhi Zhu , Hanshu Yan , Shilin Lu , Jian Yang

Sequential models achieve state-of-the-art results in audio, visual and textual domains with respect to both estimating the data distribution and generating high-quality samples. Efficient sampling for this class of models has however…

Singing voice conversion is to convert the source singing voice into the target singing voice except for the content. Currently, flow-based models can complete the task of voice conversion, but they struggle to effectively extract latent…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-10 Hui Li , Hongyu Wang , Zhijin Chen , Bohan Sun , Bo Li

The intrinsic link between facial motion and speech is often overlooked in generative modeling, where talking head synthesis and text-to-speech (TTS) are typically addressed as separate tasks. This paper introduces JAM-Flow, a unified…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Mingi Kwon , Joonghyuk Shin , Jaeseok Jung , Jaesik Park , Youngjung Uh

Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech…

Sound · Computer Science 2024-04-02 Xiang Li , Fan Bu , Ambuj Mehrish , Yingting Li , Jiale Han , Bo Cheng , Soujanya Poria

Current discriminative depth estimation methods often produce blurry artifacts, while generative approaches suffer from slow sampling due to curvatures in the noise-to-depth transport. Our method addresses these challenges by framing depth…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Ming Gui , Johannes Schusterbauer , Ulrich Prestel , Pingchuan Ma , Dmytro Kotovenko , Olga Grebenkova , Stefan Andreas Baumann , Vincent Tao Hu , Björn Ommer

Voice Conversion (VC) aims to modify a speaker's timbre while preserving linguistic content. While recent VC models achieve strong performance, most struggle in real-time streaming scenarios due to high latency, dependence on ASR modules,…

Sound · Computer Science 2025-10-13 Zhao Guo , Ziqian Ning , Guobin Ma , Lei Xie

Video generation requires modeling a vast spatiotemporal space, which demands significant computational resources and data usage. To reduce the complexity, the prevailing approaches employ a cascaded architecture to avoid direct training…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Yang Jin , Zhicheng Sun , Ningyuan Li , Kun Xu , Kun Xu , Hao Jiang , Nan Zhuang , Quzhe Huang , Yang Song , Yadong Mu , Zhouchen Lin

This paper integrates graph-to-sequence into an end-to-end text-to-speech framework for syntax-aware modelling with syntactic information of input text. Specifically, the input text is parsed by a dependency parsing module to form a…

Sound · Computer Science 2023-09-19 Jianzong Wang , Xulong Zhang , Aolan Sun , Ning Cheng , Jing Xiao

Our research introduces an innovative framework for video-to-audio synthesis, which solves the problems of audio-video desynchronization and semantic loss in the audio. By incorporating a semantic alignment adapter and a temporal…

Sound · Computer Science 2024-09-16 Zhiqi Huang , Dan Luo , Jun Wang , Huan Liao , Zhiheng Li , Zhiyong Wu

Speech enhancement (SE) improves degraded speech's quality, with generative models like flow matching gaining attention for their outstanding perceptual quality. However, the flow-based model requires multiple numbers of function…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-26 Jiahe Wang , Hongyu Wang , Wei Wang , Lei Yang , Chenda Li , Wangyou Zhang , Lufen Tan , Yanmin Qian

Current Text-to-audio (TTA) models mainly use coarse text descriptions as inputs to generate audio, which hinders models from generating audio with fine-grained control of content and style. Some studies try to improve the granularity by…

Audio and Speech Processing · Electrical Eng. & Systems 2025-04-01 Yuanyuan Wang , Hangting Chen , Dongchao Yang , Zhiyong Wu , Xixin Wu

We introduce OmniFlow, a novel generative model designed for any-to-any generation tasks such as text-to-image, text-to-audio, and audio-to-image synthesis. OmniFlow advances the rectified flow (RF) framework used in text-to-image models to…

Audio is indispensable for real-world video, yet generation models have largely overlooked audio components. Current approaches to producing audio-visual content often rely on cascaded pipelines, which increase cost, accumulate errors, and…

Text-to-video and image-to-video generation have made rapid progress in visual quality, but they remain limited in controlling the precise timing of motion. In contrast, audio provides temporal cues aligned with video motion, making it a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Jibin Song , Mingi Kwon , Jaeseok Jeong , Youngjung Uh