Results 251 to 260 of about 4,915,608 (331)

GVMGen: A General Video-to-Music Generation Model with Hierarchical Attentions

AAAI Conference on Artificial Intelligence
Composing music for video is essential yet challenging, leading to a growing interest in automating music generation for video applications. Existing approaches often struggle to achieve robust music-video correspondence and generative diversity ...
Heda Zuo, W. You, Junxian Wu, Shihong Ren, Pei Chen, Mingxu Zhou, Yujia Lu, Lingyun Sun   +7 more
semanticscholar   +1 more source

Benchmarking Music Generation Models and Metrics via Human Preference Studies

IEEE International Conference on Acoustics, Speech, and Signal Processing
Recent advancements have brought generated music closer to human-created compositions, yet evaluating these models remains challenging. While human preference is the gold standard for assessing quality, translating these subjective judgments into ...
Florian Grötschla, Ahmet Solak, Luca A. Lanzendörfer, R. Wattenhofer   +3 more
semanticscholar   +1 more source

Analyzable Chain-of-Musical-Thought Prompting for High-Fidelity Music Generation

arXiv.org
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 composition, potentially
Max W. Y. Lam, Yijin Xing, Weiya You, Jingcheng Wu, Zongyu Yin, Fuqiang Jiang, Hangyu Liu, Feng Liu, Xingda Li, Wei Lu, Hanyu Chen, T. Feng, Tianwei Zhao, Chien-Hung Liu, Xuchen Song, Yang Li, Yahui Zhou   +16 more
semanticscholar   +1 more source

MusicGen-Stem: Multi-stem music generation and edition through autoregressive modeling

IEEE International Conference on Acoustics, Speech, and Signal Processing
While most music generation models generate a mixture of stems (in mono or stereo), we propose to train a multi-stem generative model with 3 stems (bass, drums and other) that learn the musical dependencies between them.
Simon Rouard, Robin San Roman, Yossi Adi, Axel Roebel   +3 more
semanticscholar   +1 more source

AI-Enabled Text-to-Music Generation: A Comprehensive Review of Methods, Frameworks, and Future Directions

Electronics
Text-to-music generation integrates natural language processing and music generation, enabling artificial intelligence (AI) to compose music from textual descriptions.
Yujia Zhao, Mingzhi Yang, Yujia Lin, Xiaohong Zhang, Feifei Shi, Zongjie Wang, Jianguo Ding, Huansheng Ning   +7 more
semanticscholar   +1 more source

Music for All: Representational Bias and Cross-Cultural Adaptability of Music Generation Models

North American Chapter of the Association for Computational Linguistics
The advent of Music-Language Models has greatly enhanced the automatic music generation capability of AI systems, but they are also limited in their coverage of the musical genres and cultures of the world. We present a study of the datasets and research
Atharva Mehta, Shivam Chauhan, Amirbek Djanibekov, Atharva Kulkarni, Gus G. Xia, Monojit Choudhury   +5 more
semanticscholar   +1 more source

Hybrid Learning Module-Based Transformer for Multitrack Music Generation With Music Theory

IEEE Transactions on Computational Social Systems
In recent years, multitrack music generation has garnered significant attention in both academic and industrial spheres for its versatile utilization of various instruments in collaborative settings.
Y. Tie, Xin Guo, Donghui Zhang, Jiessie Tie, Lin Qi, Yuhang Lu   +5 more
semanticscholar   +1 more source

DITTO: Diffusion Inference-Time T-Optimization for Music Generation

International Conference on Machine Learning
We propose Diffusion Inference-Time T-Optimization (DITTO), a general-purpose frame-work for controlling pre-trained text-to-music diffusion models at inference-time via optimizing initial noise latents.
Zachary Novack, Julian McAuley, Taylor Berg-Kirkpatrick, Nicholas J. Bryan   +3 more
semanticscholar   +1 more source

ClaviNet: Generate Music With Different Musical Styles

IEEE MultiMedia, 2021
Classically, the style of the generated music by deep learning models is usually governed by the training dataset. In this article, we improved this by proposing the continuous style embedding ${z}_{s}$ z s to the general formulation of variational autoencoder (VAE) to allow users to be able to condition on the style of the generated music.
Yu-Quan Lim, Chee Seng Chan, Fung Ying Loo   +2 more
openaire   +1 more source

Symbolic Music Generation with Non-Differentiable Rule Guided Diffusion

International Conference on Machine Learning
We study the problem of symbolic music generation (e.g., generating piano rolls), with a technical focus on non-differentiable rule guidance. Musical rules are often expressed in symbolic form on note characteristics, such as note density or chord ...
Yujia Huang, Adishree Ghatare, Yuanzhe Liu, Ziniu Hu, Qinsheng Zhang, C. Sastry, Siddharth Gururani, Sageev Oore, Yisong Yue   +8 more
semanticscholar   +1 more source