English
Related papers

Related papers: LaDA-Band: Language Diffusion Models for Vocal-to-…

200 papers

Training a unified model integrating video-to-audio (V2A), text-to-audio (T2A), and joint video-text-to-audio (VT2A) generation offers significant application flexibility, yet faces two unexplored foundational challenges: (1) the scarcity…

Sound · Computer Science 2026-04-30 Yusheng Dai , Zehua Chen , Yuxuan Jiang , Baolong Gao , Qiuhong Ke , Jianfei Cai , Jun Zhu

Dance-to-music (D2M) generation aims to automatically compose music that is rhythmically and temporally aligned with dance movements. Existing methods typically rely on coarse rhythm embeddings, such as global motion features or binarized…

Sound · Computer Science 2026-03-03 Jinting Wang , Chenxing Li , Li Liu

Large language model (LLM)-based text-to-speech (TTS) systems achieve remarkable naturalness via autoregressive (AR) decoding, but require N sequential steps to generate N speech tokens. We present LLaDA-TTS, which replaces the AR LLM with…

Sound · Computer Science 2026-03-30 Xiaoyu Fan , Huizhi Xie , Wei Zou , Yunzhang Chen

While Diffusion Generative Models have achieved great success on image generation tasks, how to efficiently and effectively incorporate them into speech generation especially translation tasks remains a non-trivial problem. Specifically,…

Computation and Language · Computer Science 2023-10-27 Yongxin Zhu , Zhujin Gao , Xinyuan Zhou , Zhongyi Ye , Linli Xu

While language models (LMs) paired with residual vector quantization (RVQ) tokenizers have shown promise in text-to-audio (T2A) generation, they still lag behind diffusion-based models by a non-trivial margin. We identify a critical dilemma…

Sound · Computer Science 2025-10-07 Juncheng Wang , Chao Xu , Cheng Yu , Zhe Hu , Haoyu Xie , Guoqi Yu , Lei Shang , Shujun Wang

Video-to-music (V2M) generation aims to create music that aligns with visual content. However, two main challenges persist in existing methods: (1) the lack of explicit rhythm modeling hinders audiovisual temporal alignments; (2)…

Sound · Computer Science 2025-11-13 Shulei Ji , Zihao Wang , Jiaxing Yu , Xiangyuan Yang , Shuyu Li , Songruoyao Wu , Kejun Zhang

Video-to-audio (V2A) generation aims to produce corresponding audio given silent video inputs. This task is particularly challenging due to the cross-modality and sequential nature of the audio-visual features involved. Recent works have…

Sound · Computer Science 2024-09-17 Mingjing Yi , Ming Li

Autoregressive (AR) large audio language models (LALMs) such as Qwen-2.5-Omni have achieved strong performance on audio understanding and interaction, but scaling them remains costly in data and computation, and strictly sequential decoding…

Sound · Computer Science 2026-02-02 Jiaming Zhou , Xuxin Cheng , Shiwan Zhao , Yuhang Jia , Cao Liu , Ke Zeng , Xunliang Cai , Yong Qin

In recent years, with the realistic generation results and a wide range of personalized applications, diffusion-based generative models gain huge attention in both visual and audio generation areas. Compared to the considerable advancements…

Computer Vision and Pattern Recognition · Computer Science 2024-05-27 Shiqi Yang , Zhi Zhong , Mengjie Zhao , Shusuke Takahashi , Masato Ishii , Takashi Shibuya , Yuki Mitsufuji

Recent advancements in audio generation have been spurred by the evolution of large-scale deep learning models and expansive datasets. However, the task of video-to-audio (V2A) generation continues to be a challenge, principally because of…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-20 Xinhao Mei , Varun Nagaraja , Gael Le Lan , Zhaoheng Ni , Ernie Chang , Yangyang Shi , Vikas Chandra

We present \textbf{LLaDA-o}, an effective and length-adaptive omni diffusion model for multimodal understanding and generation. LLaDA-o is built on a Mixture of Diffusion (MoD) framework that decouples discrete masked diffusion for text…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Zebin You , Xiaolu Zhang , Jun Zhou , Chongxuan Li , Ji-Rong Wen

Diffusion language models intrinsically fail to capture correlations between decoded tokens, which leads to a harsh trade-off between sampling quality and throughput. To solve this issue, we propose DiLaDiff, a variant of masked diffusion…

Machine Learning · Computer Science 2026-05-25 Jean-Marie Lemercier , Tomas Geffner , Karsten Kreis , Morteza Mardani , Arash Vahdat , Ante Jukić

Discrete masked diffusion language models such as LLaDA generate text through iterative denoising, where mask tokens are progressively replaced with predicted tokens. LLaDA2.1 introduced a Token-to-Token (T2T) editing mechanism that…

Computation and Language · Computer Science 2026-05-27 Lin Yao

Currently, high-quality, synchronized audio is synthesized using various multi-modal joint learning frameworks, leveraging video and optional text inputs. In the video-to-audio benchmarks, video-to-audio quality, semantic alignment, and…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Haomin Zhang , Chang Liu , Junjie Zheng , Zihao Chen , Chaofan Ding , Xinhan Di

This technical report presents a new paradigm for full-song symbolic music generation. Existing symbolic models operate on note-attribute tokens and suffer from extremely long sequences, limited context length, and weak support for…

Sound · Computer Science 2025-12-17 Longshen Ou , Ye Wang

Video-to-Audio (V2A) generation is essential for immersive multimedia experiences, yet its evaluation remains underexplored. Existing benchmarks typically assess diverse audio types under a unified protocol, overlooking the fine-grained…

Sound · Computer Science 2026-04-14 Qian Zhang , Yuqin Cao , Yixuan Gao , Xiongkuo Min

Most music generation models directly generate a single music mixture. To allow for more flexible and controllable generation, the Multi-Source Diffusion Model (MSDM) has been proposed to model music as a mixture of multiple instrumental…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-18 Zhongweiyang Xu , Debottam Dutta , Yu-Lin Wei , Romit Roy Choudhury

Discrete diffusion models have recently shown great promise for modeling complex discrete data, with masked diffusion models (MDMs) offering a compelling trade-off between quality and generation speed. MDMs denoise by progressively…

Machine Learning · Computer Science 2026-04-15 Tianyu Xie , Shuchen Xue , Zijin Feng , Tianyang Hu , Jiacheng Sun , Zhenguo Li , Cheng Zhang

When hearing music, it is natural for people to dance to its rhythm. Automatic dance generation, however, is a challenging task due to the physical constraints of human motion and rhythmic alignment with target music. Conventional…

Graphics · Computer Science 2023-08-08 Qiaosong Qi , Le Zhuo , Aixi Zhang , Yue Liao , Fei Fang , Si Liu , Shuicheng Yan

Extracting individual elements from music mixtures is a valuable tool for music production and practice. While neural networks optimized to mask or transform mixture spectrograms into the individual source(s) have been the leading approach,…

Sound · Computer Science 2025-11-26 Genís Plaja-Roglans , Yun-Ning Hung , Xavier Serra , Igor Pereira