English
Related papers

Related papers: Autoregressive Diffusion Transformer for Text-to-S…

200 papers

In this work, we empirically study Diffusion Transformers (DiTs) for text-to-image generation, focusing on architectural choices, text-conditioning strategies, and training protocols. We evaluate a range of DiT-based…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Chen Chen , Rui Qian , Wenze Hu , Tsu-Jui Fu , Jialing Tong , Xinze Wang , Lezhi Li , Bowen Zhang , Alex Schwing , Wei Liu , Yinfei Yang

Diffusion models have significantly improved the quality and diversity of audio generation but are hindered by slow inference speed. Rectified flow enhances inference speed by learning straight-line ordinary differential equation (ODE)…

Sound · Computer Science 2025-05-29 Junqi Zhao , Jinzheng Zhao , Haohe Liu , Yun Chen , Lu Han , Xubo Liu , Mark Plumbley , Wenwu Wang

Controllable text-to-audio generation aims to synthesize audio from textual descriptions while satisfying user-specified constraints, including event types, temporal sequences, and onset and offset timestamps. This enables precise control…

Sound · Computer Science 2026-02-10 Yisu Liu , Chenxing Li , Wanqian Zhang , Wenfu Wang , Meng Yu , Ruibo Fu , Zheng Lin , Weiping Wang , Dong Yu

The rapid development of large-scale text-to-speech (TTS) models has led to significant advancements in modeling diverse speaker prosody and voices. However, these models often face issues such as slow inference speeds, reliance on complex…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-17 Yinghao Aaron Li , Xilin Jiang , Cong Han , Nima Mesgarani

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hinder their applications to text-to-speech deployment. Through…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-14 Rongjie Huang , Zhou Zhao , Huadai Liu , Jinglin Liu , Chenye Cui , Yi Ren

This paper presents Diffusion via Autoregressive models (D-AR), a new paradigm recasting the image diffusion process as a vanilla autoregressive procedure in the standard next-token-prediction fashion. We start by designing the tokenizer…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Ziteng Gao , Mike Zheng Shou

Text-guided image generation has witnessed unprecedented progress due to the development of diffusion models. Beyond text and image, sound is a vital element within the sphere of human perception, offering vivid representations and…

Graphics · Computer Science 2023-06-21 Yue Yang , Kaipeng Zhang , Yuying Ge , Wenqi Shao , Zeyue Xue , Yu Qiao , Ping Luo

Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation? To circumvent the discrete nature of text data, we can simply project tokens in a continuous space of embeddings, as…

We propose a novel talking head synthesis pipeline called "DiT-Head", which is based on diffusion transformers and uses audio as a condition to drive the denoising process of a diffusion model. Our method is scalable and can generalise to…

Artificial Intelligence · Computer Science 2023-12-12 Aaron Mir , Eduardo Alonso , Esther Mondragón

Text-to-audio (TTA) system has recently gained attention for its ability to synthesize general audio based on text descriptions. However, previous studies in TTA have limited generation quality with high computational costs. In this study,…

Sound · Computer Science 2023-09-12 Haohe Liu , Zehua Chen , Yi Yuan , Xinhao Mei , Xubo Liu , Danilo Mandic , Wenwu Wang , Mark D. Plumbley

Videos are inherently temporal sequences by their very nature. In this work, we explore the potential of modeling videos in a chronological and scalable manner with autoregressive (AR) language models, inspired by their success in natural…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Yizhuo Li , Yuying Ge , Yixiao Ge , Ying Shan , Ping Luo

Autoregressive (AR) Large Language Models (LLMs) have demonstrated significant success across numerous tasks. However, the AR modeling paradigm presents certain limitations; for instance, contemporary autoregressive LLMs are trained to…

Machine Learning · Computer Science 2025-02-10 Justin Deschenaux , Caglar Gulcehre

Existing DiT-based audio-driven avatar generation methods have achieved considerable progress, yet their broader application is constrained by limitations such as high computational overhead and the inability to synthesize long-duration…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Chaochao Li , Ruikui Wang , Liangbo Zhou , Jinheng Feng , Huaishao Luo , Huan Zhang , Youzheng Wu , Xiaodong He

This paper focuses on the task of speech-driven 3D facial animation, which aims to generate realistic and synchronized facial motions driven by speech inputs. Recent methods have employed audio-conditioned diffusion models for 3D facial…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Yifan Yang , Zhi Cen , Sida Peng , Xiangwei Chen , Yifu Deng , Xinyu Zhu , Fan Jia , Xiaowei Zhou , Hujun Bao

Current mainstream audio generation methods primarily rely on simple text prompts, often failing to capture the nuanced details necessary for multi-style audio generation. To address this limitation, the Sound Event Enhanced Prompt Adapter…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-17 Chenxu Xiong , Ruibo Fu , Shuchen Shi , Zhengqi Wen , Jianhua Tao , Tao Wang , Chenxing Li , Chunyu Qiang , Yuankun Xie , Xin Qi , Guanjun Li , Zizheng Yang

We describe a sequence-to-sequence neural network which directly generates speech waveforms from text inputs. The architecture extends the Tacotron model by incorporating a normalizing flow into the autoregressive decoder loop. Output…

Computation and Language · Computer Science 2021-02-09 Ron J. Weiss , RJ Skerry-Ryan , Eric Battenberg , Soroosh Mariooryad , Diederik P. Kingma

Recent advances in deep learning for sequential data have given rise to fast and powerful models that produce realistic videos of talking humans. The state of the art in talking face generation focuses mainly on lip-syncing, being…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Georgios Milis , Panagiotis P. Filntisis , Anastasios Roussos , Petros Maragos

This paper presents an audio-visual approach for voice separation which produces state-of-the-art results at a low latency in two scenarios: speech and singing voice. The model is based on a two-stage network. Motion cues are obtained with…

Sound · Computer Science 2022-07-20 Juan F. Montesinos , Venkatesh S. Kadandale , Gloria Haro

Recent language model-based text-to-speech (TTS) frameworks demonstrate scalability and in-context learning capabilities. However, they suffer from robustness issues due to the accumulation of errors in speech unit predictions during…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-13 Kun Zhou , Shengkui Zhao , Yukun Ma , Chong Zhang , Hao Wang , Dianwen Ng , Chongjia Ni , Nguyen Trung Hieu , Jia Qi Yip , Bin Ma

Diffusion models have exhibited remarkable capabilities in text-to-image generation. However, their performance in image-to-text generation, specifically image captioning, has lagged behind Auto-Regressive (AR) models, casting doubt on…

Artificial Intelligence · Computer Science 2024-04-17 Yuchi Wang , Shuhuai Ren , Rundong Gao , Linli Yao , Qingyan Guo , Kaikai An , Jianhong Bai , Xu Sun