中文
相关论文

相关论文: PhraseVAE and PhraseLDM: Latent Diffusion for Full…

200 篇论文

Discovering and exploring the underlying structure of multi-instrumental music using learning-based approaches remains an open problem. We extend the recent MusicVAE model to represent multitrack polyphonic measures as vectors in a latent…

机器学习 · 统计学 2018-06-04 Ian Simon , Adam Roberts , Colin Raffel , Jesse Engel , Curtis Hawthorne , Douglas Eck

Recent advances in symbolic music generation primarily rely on deep learning models such as Transformers, GANs, and diffusion models. While these approaches achieve high-quality results, they require substantial computational resources,…

Latent Diffusion Models (LDMs) rely heavily on the compressed latent space provided by Variational Autoencoders (VAEs) for high-quality image generation. Recent studies have attempted to obtain generation-friendly VAEs by directly adopting…

计算机视觉与模式识别 · 计算机科学 2026-03-17 John Page , Xuesong Niu , Kai Wu , Kun Gai

Audio-based generative models for music have seen great strides recently, but so far have not managed to produce full-length music tracks with coherent musical structure from text prompts. We show that by training a generative model on long…

声音 · 计算机科学 2024-07-30 Zach Evans , Julian D. Parker , CJ Carr , Zack Zukowski , Josiah Taylor , Jordi Pons

Generating music with coherent structure, harmonious instrumental and vocal elements remains a significant challenge in song generation. Existing language models and diffusion-based methods often struggle to balance global coherence with…

音频与语音处理 · 电气工程与系统科学 2025-10-23 Chenyu Yang , Shuai Wang , Hangting Chen , Wei Tan , Jianwei Yu , Haizhou Li

Autoregressive language models (ARMs) deliver strong likelihoods, but are inherently serial: they generate one token per forward pass, which limits throughput and inflates latency for long sequences. Diffusion Language Models (DLMs)…

Latent diffusion models (LDMs) achieve state-of-the-art image synthesis, yet their reconstruction-style denoising objective provides only indirect semantic supervision: high-level semantics emerge slowly, requiring longer training and…

计算机视觉与模式识别 · 计算机科学 2025-12-19 Giorgos Petsangourakis , Christos Sgouropoulos , Bill Psomas , Theodoros Giannakopoulos , Giorgos Sfikas , Ioannis Kakogeorgiou

Diffusion Probabilistic Models (DPMs) have emerged as the de facto approach for high-fidelity image synthesis, operating diffusion processes on continuous VAE latent, which significantly differ from the text generation methods employed by…

计算机视觉与模式识别 · 计算机科学 2024-12-30 Xiaoping Wu , Jie Hu , Xiaoming Wei

Many music AI models learn a map between music content and human-defined labels. However, many annotations, such as chords, can be naturally expressed within the music modality itself, e.g., as sequences of symbolic notes. This observation…

声音 · 计算机科学 2025-09-30 Junyan Jiang , Daniel Chin , Liwei Lin , Xuanjie Liu , Gus Xia

Recent deep music generation studies have put much emphasis on long-term generation with structures. However, we are yet to see high-quality, well-structured whole-song generation. In this paper, we make the first attempt to model a full…

声音 · 计算机科学 2024-05-17 Ziyu Wang , Lejun Min , Gus Xia

We tackle the task of long-form music generation--particularly the challenging \textbf{lyrics-to-song} problem--by introducing YuE, a family of open foundation models based on the LLaMA2 architecture. Specifically, YuE scales to trillions…

Diffusion and flow-matching models have revolutionized automatic text-to-audio generation in recent times. These models are increasingly capable of generating high quality and faithful audio outputs capturing to speech and acoustic events.…

Diffusion models have shown promise in text generation, but often struggle with generating long, coherent, and contextually accurate text. Token-level diffusion doesn't model word-order dependencies explicitly and operates on short, fixed…

计算与语言 · 计算机科学 2025-05-27 Xiaochen Zhu , Georgi Karadzhov , Chenxi Whitehouse , Andreas Vlachos

Recently, the application of diffusion probabilistic models has advanced speech enhancement through generative approaches. However, existing diffusion-based methods have focused on the generation process in high-dimensional waveform or…

声音 · 计算机科学 2025-01-20 Shengkui Zhao , Zexu Pan , Kun Zhou , Yukun Ma , Chong Zhang , Bin Ma

While deep generative models have become the leading methods for algorithmic composition, it remains a challenging problem to control the generation process because the latent variables of most deep-learning models lack good…

声音 · 计算机科学 2020-08-18 Ziyu Wang , Dingsu Wang , Yixiao Zhang , Gus Xia

Recent research on motion generation has shown significant progress in generating semantically aligned motion with singular semantics. However, when employing these models to create composite sequences containing multiple semantically…

多媒体 · 计算机科学 2025-10-17 Ho Yin Au , Jie Chen , Junkun Jiang , Jingyu Xiang

Pre-trained language models have achieved impressive results in various music understanding and generation tasks. However, existing pre-training methods for symbolic melody generation struggle to capture multi-scale, multi-dimensional…

声音 · 计算机科学 2023-09-21 Xinda Wu , Zhijie Huang , Kejun Zhang , Jiaxing Yu , Xu Tan , Tieyao Zhang , Zihao Wang , Lingyun Sun

Diffusion models have recently shown strong potential in both music generation and music source separation tasks. Although in early stages, a trend is emerging towards integrating these tasks into a single framework, as both involve…

声音 · 计算机科学 2024-12-31 Tornike Karchkhadze , Mohammad Rasool Izadi , Shlomo Dubnov

Topology optimization enables the automated design of efficient structures by optimally distributing material within a defined domain. However, traditional gradient-based methods often scale poorly with increasing resolution and…

计算工程、金融与科学 · 计算机科学 2025-08-08 Aaron Lutheran , Srijan Das , Alireza Tabarraei

We introduce the Latent Fourier Transform (LatentFT), a framework that provides novel frequency-domain controls for generative music models. LatentFT combines a diffusion autoencoder with a latent-space Fourier transform to separate musical…

声音 · 计算机科学 2026-04-21 Mason Wang , Cheng-Zhi Anna Huang