High-level musical qualities (such as emotion) are often abstract, subjective, and hard to quantify. Given these difficulties, it is not easy to learn good feature representations with supervised learning techniques, either because of the insufficiency of labels, or the subjectiveness (and hence large variance) in human-annotated labels. In this paper, we present a framework that can learn high-level feature representations with a limited amount of data, by first modelling their corresponding quantifiable low-level attributes. We refer to our proposed framework as Music FaderNets, which is inspired by the fact that low-level attributes can be continuously manipulated by separate "sliding faders" through feature disentanglement and latent regularization techniques. High-level features are then inferred from the low-level representations through semi-supervised clustering using Gaussian Mixture Variational Autoencoders (GM-VAEs). Using arousal as an example of a high-level feature, we show that the "faders" of our model are disentangled and change linearly w.r.t. the modelled low-level attributes of the generated output music. Furthermore, we demonstrate that the model successfully learns the intrinsic relationship between arousal and its corresponding low-level attributes (rhythm and note density), with only 1% of the training set being labelled. Finally, using the learnt high-level feature representations, we explore the application of our framework in style transfer tasks across different arousal states. The effectiveness of this approach is verified through a subjective listening test.
NYU Shanghai（上海纽约大学）；Queen Mary University of London（伦敦玛丽女王大学）；Tencent Inc.（腾讯公司）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）
In this study, we explore the representation mapping from the domain of visual arts to the domain of music, with which we can use visual arts as an effective handle to control music generation. Unlike most studies in multimodal representation learning that are purely data-driven, we adopt an analysis-by-synthesis approach that combines deep music representation learning with user studies. Such an approach enables us to discover \textit{interpretable} representation mapping without a huge amount of paired data. In particular, we discover that visual-to-music mapping has a nice property similar …
Drawing an analogy with automatic image completion systems, we propose Music SketchNet, a neural network framework that allows users to specify partial musical ideas guiding automatic music generation. We focus on generating the missing measures in incomplete monophonic musical pieces, conditioned on surrounding context, and optionally guided by user-specified pitch and rhythm snippets. First, we introduce SketchVAE, a novel variational autoencoder that explicitly factorizes rhythm and pitch contour to form the basis of our proposed model. Then we introduce two discriminative architectures, Sk…
Beihang University（北京航空航天大学）；Charterhouse School（查特豪斯公学）；Sea AI Lab
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 Controllabl…
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 interpretability. Inspired by the content-style disentanglement idea, we design a novel architecture, under the VAE framework, that effectively learns two interpretable latent factors of polyphonic music: chord and texture. The current model focuses on learning 8-beat long piano composition segments. We show that such chord-texture disentanglement provides a controllable g…
Recent advances in deep learning have expanded possibilities to generate music, but generating a customizable full piece of music with consistent long-term structure remains a challenge. This paper introduces MusicFrameworks, a hierarchical music structure representation and a multi-step generative process to create a full-length melody guided by long-term repetitive structure, chord, melodic contour, and rhythm constraints. We first organize the full melody with section and phrase-level structure. To generate melody in each phrase, we generate rhythm and basic melody using two separate transf…
Improving controllability or the ability to manipulate one or more attributes of the generated data has become a topic of interest in the context of deep generative models of music. Recent attempts in this direction have relied on learning disentangled representations from data such that the underlying factors of variation are well separated. In this paper, we focus on the relationship between disentanglement and controllability by conducting a systematic study using different supervised disentanglement learning algorithms based on the Variational Auto-Encoder (VAE) architecture. Our experimen…
The variational auto-encoder has become a leading framework for symbolic music generation, and a popular research direction is to study how to effectively control the generation process. A straightforward way is to control a model using different conditions during inference. However, in music practice, conditions are usually sequential (rather than simple categorical labels), involving rich information that overlaps with the learned representation. Consequently, the decoder gets confused about whether to "listen to" the latent representation or the condition, and sometimes just ignores the con…
ImprovNet -- Generating Controllable Musical Improvisations with Iterative Corruption Refinement
Electronic Engineering and Computer Science Department, Queen Mary University of London, UK（伦敦大学女王学院电子工程与计算机科学系）；Information Systems, Technology, and Design, Singapore University of Technology and Design, Singapore（新加坡科技设计大学信息系统、科技与设计系）
MusicLayout: Explicit Structural Planning for Controllable Text-to-Music Generation
College of Artificial Intelligence, Zhejiang University（浙江大学人工智能学院）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Innovation Center of Yangtze River Delta, Zhejiang University（浙江大学长三角创新中心）；The Chinese University of Hong Kong（香港中文大学）；Shandong University（山东大学）；Chu Kochen Honors College, Zhejiang University（浙江大学竺可桢学院）；Ant Group（蚂蚁集团）
We introduce Jukebox, a model that generates music with singing in the raw audio domain. We tackle the long context of raw audio using a multi-scale VQ-VAE to compress it to discrete codes, and modeling those using autoregressive Transformers. We show that the combined model at scale can generate high-fidelity and diverse songs with coherence up to multiple minutes. We can condition on artist and genre to steer the musical and vocal style, and on unaligned lyrics to make the singing more controllable. We are releasing thousands of non cherry-picked samples at https://jukebox.openai.com, along …
Singapore University of Technology and Design（新加坡科技设计大学）；Institute of High Performance Computing, A*STAR（新加坡科技研究局高性能计算研究所）；Yong Siew Toh Conservatory of Music, National University of Singapore（新加坡大学杨秀桃音乐学院）
In this paper, we learn disentangled representations of timbre and pitch for musical instrument sounds. We adapt a framework based on variational autoencoders with Gaussian mixture latent distributions. Specifically, we use two separate encoders to learn distinct latent spaces for timbre and pitch, which form Gaussian mixture components representing instrument identity and pitch, respectively. For reconstruction, latent variables of timbre and pitch are sampled from corresponding mixture components, and are concatenated as the input to a decoder. We show the model efficacy by latent space visu…
Institute of Computational Perception, Johannes Kepler University Linz（林茨约翰内斯·开普勒大学计算感知研究所）
Fast and user-controllable music generation could enable novel ways of composing or performing music. However, state-of-the-art music generation systems require large amounts of data and computational resources for training, and are slow at inference. This makes them impractical for real-time interactive use. In this work, we introduce Musika, a music generation system that can be trained on hundreds of hours of music using a single consumer GPU, and that allows for much faster than real-time generation of music of arbitrary length on a consumer CPU. We achieve this by first learning a compact…
University of Sussex（萨塞克斯大学）；Singapore University of Technology and Design（新加坡科技设计大学）
Many of the music generation systems based on neural networks are fully autonomous and do not offer control over the generation process. In this research, we present a controllable music generation system in terms of tonal tension. We incorporate two tonal tension measures based on the Spiral Array Tension theory into a variational autoencoder model. This allows us to control the direction of the tonal tension throughout the generated piece, as well as the overall level of tonal tension. Given a seed musical fragment, stemming from either the user input or from directly sampling from the laten…
Singapore University of Technology and Design（新加坡科技设计大学）；Institute of High Performance Computing, A*STAR（新加坡A*STAR高性能计算研究院）
We present a controllable neural audio synthesizer based on Gaussian Mixture Variational Autoencoders (GM-VAE), which can generate realistic piano performances in the audio domain that closely follows temporal conditions of two essential style features for piano performances: articulation and dynamics. We demonstrate how the model is able to apply fine-grained style morphing over the course of synthesizing the audio. This is based on conditions which are latent variables that can be sampled from the prior or inferred from other pieces. One of the envisioned use cases is to inspire creative and…
From Generality to Mastery: Composer-Style Symbolic Music Generation via Large-Scale Pre-training
Department of Mathematics University of California, San Diego（数学系加州大学圣地亚哥分校）；Department of Computer Science and Engineering University of California, San Diego（计算机科学与工程系加州大学圣地亚哥分校）
Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）；University of Edinburgh（爱丁堡大学）；Meitu Inc（美图公司）；The Chinese University of Hong Kong（香港中文大学）；Beihang University（北京航空航天大学）
Singapore University of Technology and Design（新加坡科技设计大学）；National University of Singapore（新加坡国立大学）
The field of automatic music composition has seen great progress in the last few years, much of which can be attributed to advances in deep neural networks. There are numerous studies that present different strategies for generating sheet music from scratch. The inclusion of high-level musical characteristics (e.g., perceived emotional qualities), however, as conditions for controlling the generation output remains a challenge. In this paper, we present a novel approach for calculating the valence (the positivity or negativity of the perceived emotion) of a chord progression within a lead shee…
Q&A: Query-Based Representation Learning for Multi-Track Symbolic Music re-Arrangement
Institute of Data Science, NUS（新加坡国立大学数据科学研究所）；Integrative Sciences and Engineering Programme, NUS Graduate School（新加坡国立大学研究生院综合科学与工程项目）；Music X Lab, NYU Shanghai（上海纽约大学Music X实验室）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；School of Computing, NUS（新加坡国立大学计算学院）
