English
Related papers

Related papers: SqueezeComposer: Temporal Speed-up is A Simple Tri…

200 papers

Autoregressive (AR) models have demonstrated impressive capabilities in generating high-fidelity music. However, the conventional next-token prediction paradigm in AR models does not align with the human creative process in music…

Long-form audio understanding poses significant challenges for large audio language models (LALMs) due to the extreme length of audio sequences and the need to reason over heterogeneous acoustic cues distributed over time, such as speech…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-26 Masao Someki , Chien-yu Huang , Siddhant Arora , Samuele Cornell , Markus Müller , Nathan Susanj , Rupak V Swaminathan , Grant P Strimel , Jing Liu , Shinji Watanabe

Recent advancements in audio generation have enabled the creation of high-fidelity audio clips from free-form textual descriptions. However, temporal relationships, a critical feature for audio content, are currently underrepresented in…

Sound · Computer Science 2024-07-04 Zeyu Xie , Xuenan Xu , Zhizheng Wu , Mengyue Wu

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…

Sound · Computer Science 2024-04-23 Zhengcong Fei , Mingyuan Fan , Junshi Huang

Current architectures for video understanding mainly build upon 3D convolutional blocks or 2D convolutions with additional operations for temporal modeling. However, these methods all regard the temporal axis as a separate dimension of the…

Computer Vision and Pattern Recognition · Computer Science 2024-05-15 Yingjie Zhai , Wenshuo Li , Yehui Tang , Xinghao Chen , Yunhe Wang

Neural audio synthesis methods now allow specifying ideas in natural language. However, these methods produce results that cannot be easily tweaked, as they are based on large latent spaces and up to billions of uninterpretable parameters.…

Sound · Computer Science 2024-06-04 Manuel Cherep , Nikhil Singh , Jessica Shand

Autoregressive language models dominate modern text generation, yet their sequential nature introduces fundamental limitations: decoding is slow, and maintaining global coherence remains challenging. Diffusion models offer a promising…

Computation and Language · Computer Science 2026-01-06 Viacheslav Meshchaninov , Egor Chimbulatov , Alexander Shabalin , Aleksandr Abramov , Dmitry Vetrov

Lyric-to-melody generation is a highly challenging task in the field of AI music generation. Due to the difficulty of learning strict yet weak correlations between lyrics and melodies, previous methods have suffered from weak…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-16 Li Chai , Donglin Wang

AI music generation has advanced rapidly, with models like diffusion and autoregressive algorithms enabling high-fidelity outputs. These tools can alter styles, mix instruments, or isolate them. Since sound can be visualized as…

Autoregressive models are widely used for tasks such as image and audio generation. The sampling process of these models, however, does not allow interruptions and cannot adapt to real-time computational resources. This challenge impedes…

Machine Learning · Computer Science 2021-02-24 Yilun Xu , Yang Song , Sahaj Garg , Linyuan Gong , Rui Shu , Aditya Grover , Stefano Ermon

Autoregressive video diffusion models enable open-ended generation through local attention and KV caching. However, existing training-free long-video optimization methods mainly focus on stable extension under a single prompt, making them…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Mingqiang Wu , Weilun Feng , Zhefeng Zhang , Haotong Qin , Yuqi Li , Guoxin Fan , Xiaokun Liu , Zhulin An , Libo Huang , Yongjun Xu , Chuanguang Yang

We introduce VampNet, a masked acoustic token modeling approach to music synthesis, compression, inpainting, and variation. We use a variable masking schedule during training which allows us to sample coherent music from the model by…

Sound · Computer Science 2023-07-13 Hugo Flores Garcia , Prem Seetharaman , Rithesh Kumar , Bryan Pardo

In this work, we introduce the demonstration of symbolic music generation, focusing on providing short musical motifs that serve as the central theme of the narrative. For the generation, we adopt an autoregressive model which takes musical…

Gradient-type distributed optimization methods have blossomed into one of the most important tools for solving a minimization learning task over a networked agent system. However, only one gradient update per iteration is difficult to…

Optimization and Control · Mathematics 2024-03-06 Mou Wu , Haibin Liao , Zhengtao Ding , Yonggang Xiao

Despite the central role that melody plays in music perception, it remains an open challenge in music information retrieval to reliably detect the notes of the melody present in an arbitrary music recording. A key challenge in melody…

Sound · Computer Science 2022-12-06 Chris Donahue , John Thickstun , Percy Liang

Generating high-fidelity images of humans with fine-grained control over attributes such as hairstyle and clothing remains a core challenge in personalized text-to-image synthesis. While prior methods emphasize identity preservation from a…

Computer Vision and Pattern Recognition · Computer Science 2025-10-17 Guocheng Gordon Qian , Daniil Ostashev , Egor Nemchinov , Avihay Assouline , Sergey Tulyakov , Kuan-Chieh Jackson Wang , Kfir Aberman

Generative models can produce synthetic patient records for analytical tasks when real data is unavailable or limited. However, current methods struggle with adhering to domain-specific knowledge and removing invalid data. We present…

Machine Learning · Computer Science 2023-12-22 Brandon Theodorou , Shrusti Jain , Cao Xiao , Jimeng Sun

Despite the innovations in deep learning and generative AI, creating long term structure as well as the layers of repeated structure common in musical works remains an open challenge in music generation. We propose an attention layer that…

Sound · Computer Science 2024-06-27 Sophia Hager , Kathleen Hablutzel , Katherine M. Kinnaird

Neural autoencoders underpin generative models. Practical, large-scale use of neural autoencoders for generative modeling necessitates fast encoding, low latent rates, and a single model across representations. Existing approaches are…

Sound · Computer Science 2026-02-23 Jonah Casebeer , Ge Zhu , Zhepei Wang , Nicholas J. Bryan

This paper addresses the problem of cross-modal musical piece identification and retrieval: finding the appropriate recording(s) from a database given a sheet music query, and vice versa, working directly with audio and scanned sheet music…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-27 Luis Carvalho , Gerhard Widmer