52 citations · 333 across the 67 of their papers we have counts for
12 papers · 1 filter
CalliPaint: Chinese Calligraphy Inpainting with Diffusion Model
Qisheng Liao, Zhinuo Wang, Muhammad Abdul-Mageed +1
Chinese calligraphy can be viewed as a unique form of visual art. Recent advancements in computer vision hold significant potential for the future development of generative models…
Content-based Controls For Music Large Language Modeling
Liwei Lin, Gus Xia, Junyan Jiang +1
Recent years have witnessed a rapid growth of large-scale language models in the domain of music audio. Such models enable end-to-end generation of higher-quality music, and some a…
Structured Multi-Track Accompaniment Arrangement via Style Prior Modelling
Jingwei Zhao, Gus Xia, Ziyu Wang +1
In the realm of music AI, arranging rich and structured multi-track accompaniments from a simple lead sheet presents significant challenges. Such challenges include maintaining tra…
Loop Copilot: Conducting AI Ensembles for Music Generation and Iterative Editing
Yixiao Zhang, Akira Maezawa, Gus Xia +2
Creating music is iterative, requiring varied methods at each stage. However, existing AI music systems fall short in orchestrating multiple subsystems for diverse needs. To addres…
Motif-Centric Representation Learning for Symbolic Music
Yuxuan Wu, Roger B. Dannenberg, Gus Xia
Music motif, as a conceptual building block of composition, is crucial for music structure analysis and automatic composition. While human listeners can identify motifs easily, exi…
Polyffusion: A Diffusion Model for Polyphonic Score Generation with Internal and External Controls
Lejun Min, Junyan Jiang, Gus Xia +1
We propose Polyffusion, a diffusion model that generates polyphonic music scores by regarding music as image-like piano roll representations. The model is capable of controllable m…
On the Effectiveness of Speech Self-supervised Learning for Music
Yinghao Ma, Ruibin Yuan, Yizhi Li +12
Self-supervised learning (SSL) has shown promising results in various speech and natural language processing applications. However, its efficacy in music information retrieval (MIR…
Q&A: Query-Based Representation Learning for Multi-Track Symbolic Music re-Arrangement
Jingwei Zhao, Gus Xia, Ye Wang
Music rearrangement is a common music practice of reconstructing and reconceptualizing a piece using new composition or instrumentation styles, which is also an important task of a…
MARBLE: Music Audio Representation Benchmark for Universal Evaluation
Ruibin Yuan, Yinghao Ma, Yizhi Li +22
In the era of extensive intersection between art and Artificial Intelligence (AI), such as image generation and fiction co-creation, AI for music remains relatively nascent, partic…
MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training
Yizhi Li, Ruibin Yuan, Ge Zhang +17
Self-supervised learning (SSL) has recently emerged as a promising paradigm for training generalisable models on large-scale data in the fields of vision, text, and speech. Althoug…
Calliffusion: Chinese Calligraphy Generation and Style Transfer with Diffusion Modeling
Qisheng Liao, Gus Xia, Zhinuo Wang
In this paper, we propose Calliffusion, a system for generating high-quality Chinese calligraphy using diffusion models. Our model architecture is based on DDPM (Denoising Diffusio…
Learning Interpretable Low-dimensional Representation via Physical Symmetry
Xuanjie Liu, Daniel Chin, Yichen Huang +1
We have recently seen great progress in learning interpretable music representations, ranging from basic factors, such as pitch and timbre, to high-level concepts, such as chord an…