中文
相关论文

相关论文: SoundCTM: Unifying Score-based and Consistency Mod…

200 篇论文

Recent advancements in Latent Diffusion Models (LDMs) have propelled them to the forefront of various generative tasks. However, their iterative sampling process poses a significant computational burden, resulting in slow generation speeds…

音频与语音处理 · 电气工程与系统科学 2024-07-10 Huadai Liu , Rongjie Huang , Yang Liu , Hengyuan Cao , Jialei Wang , Xize Cheng , Siqi Zheng , Zhou Zhao

Timestep distillation is an effective approach for improving the generation efficiency of diffusion models. The Consistency Model (CM), as a trajectory-based framework, demonstrates significant potential due to its strong theoretical…

计算机视觉与模式识别 · 计算机科学 2025-11-26 Bao Tang , Shuai Zhang , Yueting Zhu , Jijun Xiang , Xin Yang , Li Yu , Wenyu Liu , Xinggang Wang

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…

声音 · 计算机科学 2024-04-02 Xiang Li , Fan Bu , Ambuj Mehrish , Yingting Li , Jiale Han , Bo Cheng , Soujanya Poria

Autoregressive (AR) models with diffusion heads have recently achieved strong text-to-audio performance, yet their iterative decoding and multi-step sampling process introduce high-latency issues. To address this bottleneck, we propose a…

Distilling latent diffusion models (LDMs) into ones that are fast to sample from is attracting growing research interest. However, the majority of existing methods face two critical challenges: (1) They hinge on long training using a huge…

计算机视觉与模式识别 · 计算机科学 2024-11-08 Qingsong Xie , Zhenyi Liao , Zhijie Deng , Chen chen , Haonan Lu

Diffusion models have shown strong performance in speech enhancement, but their real-time applicability has been limited by multi-step iterative sampling. Consistency distillation has recently emerged as a promising alternative by…

音频与语音处理 · 电气工程与系统科学 2026-05-19 Liang Xu , Longfei Felix Yan , W. Bastiaan Kleijn

Consistency models have exhibited remarkable capabilities in facilitating efficient image/video generation, enabling synthesis with minimal sampling steps. It has proven to be advantageous in mitigating the computational burdens associated…

声音 · 计算机科学 2024-04-23 Zhengcong Fei , Mingyuan Fan , Junshi Huang

Diffusion-based text-to-video (T2V) models have achieved significant success but continue to be hampered by the slow sampling speed of their iterative sampling processes. To address the challenge, consistency models have been proposed to…

计算机视觉与模式识别 · 计算机科学 2024-10-14 Jiachen Li , Weixi Feng , Tsu-Jui Fu , Xinyi Wang , Sugato Basu , Wenhu Chen , William Yang Wang

Despite their strong performances on many generative tasks, diffusion models require a large number of sampling steps in order to generate realistic samples. This has motivated the community to develop effective methods to distill…

计算机视觉与模式识别 · 计算机科学 2024-10-23 Weijian Luo , Zemin Huang , Zhengyang Geng , J. Zico Kolter , Guo-jun Qi

Despite imperfect score-matching causing drift in training and sampling distributions of diffusion models, recent advances in diffusion-based acoustic models have revolutionized data-sufficient single-speaker Text-to-Speech (TTS)…

音频与语音处理 · 电气工程与系统科学 2023-09-01 Heyang Xue , Shuai Guo , Pengcheng Zhu , Mengxiao Bi

Distribution Matching Distillation (DMD) distills score-based generative models into efficient one-step generators, without requiring a one-to-one correspondence with the sampling trajectories of their teachers. Yet, the limited capacity of…

计算机视觉与模式识别 · 计算机科学 2026-03-26 Xiangyu Fan , Zesong Qiu , Zhuguanyu Wu , Fanzhou Wang , Zhiqian Lin , Tianxiang Ren , Dahua Lin , Ruihao Gong , Lei Yang

The pursuit of efficient and controllable high-quality content generation remains a central challenge in artificial intelligence-generated content (AIGC). While one-step generators, enabled by diffusion distillation techniques, offer…

机器学习 · 计算机科学 2025-06-25 Yihong Luo , Shuchen Xue , Tianyang Hu , Jing Tang

Recent advancements in text-to-3D generation improve the visual quality of Score Distillation Sampling (SDS) and its variants by directly connecting Consistency Distillation (CD) to score distillation. However, due to the imbalance between…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Jiahao Zhu , Zixuan Chen , Guangcong Wang , Xiaohua Xie , Yi Zhou

Score distillation sampling (SDS) and its variants have greatly boosted the development of text-to-3D generation, but are vulnerable to geometry collapse and poor textures yet. To solve this issue, we first deeply analyze the SDS and find…

计算机视觉与模式识别 · 计算机科学 2024-06-14 Zike Wu , Pan Zhou , Xuanyu Yi , Xiaoding Yuan , Hanwang Zhang

While recent diffusion-based generative image codecs have shown impressive performance, their iterative sampling process introduces unpleasing latency. In this work, we revisit the design of a diffusion-based codec and argue that multi-step…

计算机视觉与模式识别 · 计算机科学 2025-11-27 Naifu Xue , Zhaoyang Jia , Jiahao Li , Bin Li , Yuan Zhang , Yan Lu

Audio token modeling has become a powerful framework for speech synthesis, with two-stage approaches employing semantic tokens remaining prevalent. In this paper, we aim to simplify this process by introducing a semantic knowledge…

声音 · 计算机科学 2024-09-18 Gerard I. Gállego , Roy Fejgin , Chunghsin Yeh , Xiaoyu Liu , Gautam Bhattacharya

Generative models for speech synthesis face a fundamental trade-off: discrete tokens ensure stability but sacrifice expressivity, while continuous signals retain acoustic richness but suffer from error accumulation due to task entanglement.…

Generating high-quality 3D assets from textual descriptions remains a pivotal challenge in computer graphics and vision research. Due to the scarcity of 3D data, state-of-the-art approaches utilize pre-trained 2D diffusion priors, optimized…

计算机视觉与模式识别 · 计算机科学 2024-10-14 Ling Yang , Zixiang Zhang , Junlin Han , Bohan Zeng , Runjia Li , Philip Torr , Wentao Zhang

Significant advances have been made in the sampling efficiency of diffusion models and flow matching models, driven by Consistency Distillation (CD), which trains a student model to mimic the output of a teacher model at a later timestep.…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Yunpeng Liu , Boxiao Liu , Yi Zhang , Xingzhong Hou , Guanglu Song , Yu Liu , Haihang You

The emergence of multi-codebook neutral audio codecs such as Residual Vector Quantization (RVQ) and Group Vector Quantization (GVQ) has significantly advanced Large-Language-Model (LLM) based Text-to-Speech (TTS) systems. These codecs are…

声音 · 计算机科学 2025-05-26 Rui Wang , Qianguo Sun , Tianrong Chen , Zhiyun Zeng , Junlong Wu , Jiaxing Zhang
‹ 上一页 1 2 3 10 下一页 ›