Video Background Music Generation with Controllable Music Transformer

Abstract

In this work, we address the task of video background music generation. Some previous works achieve effective music generation but are unable to generate melodious music tailored to a particular video, and none of them considers the video-music rhythmic consistency. To generate the background music that matches the given video, we first establish the rhythmic relations between video and background music. In particular, we connect timing, motion speed, and motion saliency from video with beat, simu-note density, and simu-note strength from music, respectively. We then propose CMT, a Controllable Music Transformer that enables local control of the aforementioned rhythmic features and global control of the music genre and instruments. Objective and subjective evaluations show that the generated background music has achieved satisfactory compatibility with the input videos, and at the same time, impressive music quality. Code and models are available at https://github.com/wzk1015/video-bgm-generation.

Accepted to ACM Multimedia 2021. Project website at https://wzk1015.github.io/cmt/

References in corpus (11)

• YouTube-8M: A Large-Scale Video Classification Benchmark
• SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
• Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
• GANSynth: Adversarial Neural Audio Synthesis
• The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures
• Audeo: Audio Generation for a Silent Performance Video
• LakhNES: Improving multi-instrumental music generation with cross-domain pre-training
• PIANOTREE VAE: Structured Representation Learning for Polyphonic Music
• Multi-Instrumentalist Net: Unsupervised Generation of Music from Body Movements
• Foley Music: Learning to Generate Music from Videos
• PopMAG: Pop Music Accompaniment Generation

Cited by in corpus (6)

• Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model
• Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey
• Sounding Video Generator: A Unified Framework for Text-guided Sounding Video Generation
• The NES Video-Music Database: A Dataset of Symbolic Video Game Music Paired with Gameplay Videos
• Enhancing Video Music Recommendation with Transformer-Driven Audio-Visual Embeddings
• Zero-Effort Image-to-Music Generation: An Interpretable RAG-based VLM Approach