English
Related papers

Related papers: IntMeanFlow: Few-step Speech Generation with Integ…

200 papers

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

MeanFlow (MF) has recently been established as a framework for one-step generative modeling. However, its ``fastforward'' nature introduces key challenges in both the training objective and the guidance mechanism. First, the original MF's…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Zhengyang Geng , Yiyang Lu , Zongze Wu , Eli Shechtman , J. Zico Kolter , Kaiming He

Although diffusion models in text-to-speech have become a popular choice due to their strong generative ability, the intrinsic complexity of sampling from diffusion models harms their efficiency. Alternatively, we propose VoiceFlow, an…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-04 Yiwei Guo , Chenpeng Du , Ziyang Ma , Xie Chen , Kai Yu

Recent years have witnessed remarkable progress in Text-to-Audio Generation (TTA), providing sound creators with powerful tools to transform inspirations into vivid audio. Yet despite these advances, current TTA systems often suffer from…

Sound · Computer Science 2025-10-23 Xiquan Li , Junxi Liu , Yuzhe Liang , Zhikang Niu , Wenxi Chen , Xie Chen

MeanFlow offers a promising framework for one-step generative modeling by directly learning a mean-velocity field, bypassing expensive numerical integration. However, we find that the highly curved generative trajectories of existing models…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Xinxi Zhang , Shiwei Tan , Quang Nguyen , Quan Dao , Ligong Han , Xiaoxiao He , Tunyu Zhang , Chengzhi Mao , Dimitris Metaxas , Vladimir Pavlovic

Diffusion models have revolutionized text-to-image generation with its exceptional quality and creativity. However, its multi-step sampling process is known to be slow, often requiring tens of inference steps to obtain satisfactory results.…

Machine Learning · Computer Science 2024-03-26 Xingchao Liu , Xiwen Zhang , Jianzhu Ma , Jian Peng , Qiang Liu

Incremental text-to-speech (TTS) synthesis generates utterances in small linguistic units for the sake of real-time and low-latency applications. We previously proposed an incremental TTS method that leverages a large pre-trained language…

Sound · Computer Science 2021-09-23 Takaaki Saeki , Shinnosuke Takamichi , Hiroshi Saruwatari

Incremental text-to-speech, also known as streaming TTS, has been increasingly applied to online speech applications that require ultra-low response latency to provide an optimal user experience. However, most of the existing speech…

Sound · Computer Science 2022-12-06 Muyang Du , Chuan Liu , Jiaxing Qi , Junjie Lai

Diffusion-based generative models have greatly impacted the speech processing field in recent years, exhibiting high speech naturalness and spawning a new research direction. Their application in real-time communication is, however, still…

Signal Processing · Electrical Eng. & Systems 2026-04-22 Simon Welker , Bunlong Lay , Maris Hillemann , Tal Peer , Timo Gerkmann

Text-to-speech (TTS) systems have seen significant advancements in recent years, driven by improvements in deep learning and neural network architectures. Viewing the output speech as a data distribution, previous approaches often employ…

Diffusion and flow matching (FM) models have achieved remarkable progress in speech enhancement (SE), yet their dependence on multi-step generation is computationally expensive and vulnerable to discretization errors. Recent advances in…

Sound · Computer Science 2025-09-23 Gang Yang , Yue Lei , Wenxin Tai , Jin Wu , Jia Chen , Ting Zhong , Fan Zhou

In recent years, speech generation has seen remarkable progress, now achieving one-shot generation capability that is often virtually indistinguishable from real human voice. Integrating such advancements in speech generation with large…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-08 Paweł Budzianowski , Taras Sereda , Tomasz Cichy , Ivan Vulić

In target speaker extraction (TSE), we aim to recover target speech from a multi-talker mixture using a short enrollment utterance as reference. Recent studies on diffusion and flow-matching generators have improved target-speech fidelity.…

Sound · Computer Science 2026-03-12 Duojia Li , Shuhan Zhang , Zihan Qian , Wenxuan Wu , Shuai Wang , Qingyang Hong , Lin Li , Haizhou Li

Flow-based 3D generation models typically require dozens of sampling steps during inference. Though few-step distillation methods, particularly Consistency Models (CMs), have achieved substantial advancements in accelerating 2D diffusion…

Computer Vision and Pattern Recognition · Computer Science 2025-09-05 Zanwei Zhou , Taoran Yi , Jiemin Fang , Chen Yang , Lingxi Xie , Xinggang Wang , Wei Shen , Qi Tian

While recent advances in Text-To-Speech synthesis have yielded remarkable improvements in generating high-quality speech, research on lightweight and fast models is limited. This paper introduces FLY-TTS, a new fast, lightweight and…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-02 Yinlin Guo , Yening Lv , Jinqiao Dou , Yan Zhang , Yuehai Wang

Few-step diffusion or flow-based generative models typically distill a velocity-predicting teacher into a student that predicts a shortcut towards denoised data. This format mismatch has led to complex distillation procedures that often…

Machine Learning · Computer Science 2026-02-20 Hansheng Chen , Kai Zhang , Hao Tan , Leonidas Guibas , Gordon Wetzstein , Sai Bi

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

Limited by inference latency, existing robot manipulation policies lack sufficient real-time interaction capability with the environment. Although faster generation methods such as flow matching are gradually replacing diffusion methods,…

Robotics · Computer Science 2026-02-17 Zhenchen Dong , Jinna Fu , Jiaming Wu , Shengyuan Yu , Fulin Chen , Yide Liu

Vision-Language-Action (VLA) models based on flow matching -- such as pi0, pi0.5, and SmolVLA -- achieve state-of-the-art generalist robotic manipulation, yet their iterative denoising, typically 10 ODE steps, introduces substantial…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Wuyang Luan , Junhui Li , Weiguang Zhao , Wenjian Zhang , Tieru Wu , Rui Ma

Flow based generative models have charted an impressive path across multiple visual generation tasks by adhering to a simple principle: learning velocity representations of a linear interpolant. However, we observe that training velocity…

Computer Vision and Pattern Recognition · Computer Science 2025-09-04 Inkyu Shin , Chenglin Yang , Liang-Chieh Chen