In this work, we propose a flexible method for generating variations of discrete sequences in which tokens can be grouped into basic units, like sentences in a text or bars in music. More precisely, given a template sequence, we aim at producing novel sequences sharing perceptible similarities with the original template without relying on any annotation; so our problem of generating variations is intimately linked to the problem of learning relevant high-level representations without supervision. Our contribution is two-fold: First, we propose a self-supervised encoding technique, named Vector Quantized Contrastive Predictive Coding which allows to learn a meaningful assignment of the basic units over a discrete set of codes, together with mechanisms allowing to control the information content of these learnt discrete representations. Secondly, we show how these compressed representations can be used to generate variations of a template sequence by using an appropriate attention pattern in the Transformer architecture. We illustrate our approach on the corpus of J.S. Bach chorales where we discuss the musical meaning of the learnt discrete codes and show that our proposed method allows to generate coherent and high-quality variations of a given template.
EMelodyGen: Emotion-Conditioned Melody Generation in ABC Notation with the Musical Feature Template
Department of Music AI and Information Technology, Central Conservatory of Music（中央音乐学院音乐人工智能与信息科技系）；School of Computer Science and Technology, Fudan University（复旦大学计算机科学与技术学院）；Shanghai Key Laboratory of Intelligent Information Processing, Fudan University（复旦大学智能信息处理上海重点实验室）
Illinois Institute of Technology（伊利诺伊理工学院）；Snap Inc.（Snap公司）；Princeton University（普林斯顿大学）
We present Dance2Music-GAN (D2M-GAN), a novel adversarial multi-modal framework that generates complex musical samples conditioned on dance videos. Our proposed framework takes dance video frames and human body motions as input, and learns to generate music samples that plausibly accompany the corresponding input. Unlike most existing conditional music generation works that generate specific types of mono-instrumental sounds using symbolic audio representations (e.g., MIDI), and that usually rely on pre-defined musical synthesizers, in this work we generate dance music in complex styles (e.g.,…
Automatic music generation systems have gained in popularity and sophistication as advances in cloud computing have enabled large-scale complex computations such as deep models and optimization algorithms on personal devices. Yet, they still face an important challenge, that of long-term structure, which is key to conveying a sense of musical coherence. We present the MorpheuS music generation system designed to tackle this problem. MorpheuS' novel framework has the ability to generate polyphonic pieces with a given tension profile and long- and short-term repeated pattern structures. A mathem…
Université Côte d’Azur（蔚蓝海岸大学）；CNRS（法国国家科学研究中心）；OCA（蔚蓝海岸天文台）；IRIT（图卢兹计算机科学研究所）；Université de Bretagne Sud（南布列塔尼大学）；IRISA（法国国家信息与自动化研究所-雷恩第一大学联合研究中心）；Aix-Marseille Université（艾克斯-马赛大学）；LIF（计算机科学实验室）
Many spectral unmixing methods rely on the non-negative decomposition of spectral data onto a dictionary of spectral templates. In particular, state-of-the-art music transcription systems decompose the spectrogram of the input signal onto a dictionary of representative note spectra. The typical measures of fit used to quantify the adequacy of the decomposition compare the data and template entries frequency-wise. As such, small displacements of energy from a frequency bin to another as well as variations of timber can disproportionally harm the fit. We address these issues by means of optimal …
NYU Shanghai（上海纽约大学）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；QMUL（伦敦玛丽女王大学）
Music contains hierarchical structures beyond beats and measures. While hierarchical structure annotations are helpful for music information retrieval and computer musicology, such annotations are scarce in current digital music databases. In this paper, we explore a data-driven approach to automatically extract hierarchical metrical structures from scores. We propose a new model with a Temporal Convolutional Network-Conditional Random Field (TCN-CRF) architecture. Given a symbolic music score, our model takes in an arbitrary number of voices in a beat-quantized form, and predicts a 4-level hi…
Symbolic music generation has attracted increasing attention, while most methods focus on generating short piece (mostly less than 8 bars, and up to 32 bars). Generating long music calls for effective expression of the coherent music structure. Despite their success on long sequences, self-attention architectures still have challenge in dealing with long-term music as it requires additional care on the subtle music structure. In this paper, we propose to transfer the structure of training samples for new music generation, and develop a novel separable self-attention based model which enable th…
Representations in the auditory cortex might be based on mechanisms similar to the visual ventral stream; modules for building invariance to transformations and multiple layers for compositionality and selectivity. In this paper we propose the use of such computational modules for extracting invariant and discriminative audio representations. Building on a theory of invariance in hierarchical architectures, we propose a novel, mid-level representation for acoustical signals, using the empirical distributions of projections on a set of templates and their transformations. Under the assumption t…
Music that is generated by recurrent neural networks often lacks a sense of direction and coherence. We therefore propose a two-stage LSTM-based model for lead sheet generation, in which the harmonic and rhythmic templates of the song are produced first, after which, in a second stage, a sequence of melody notes is generated conditioned on these templates. A subjective listening test shows that our approach outperforms the baselines and increases perceived musical coherence.
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）；Zhejiang University（浙江大学）
Lyric-to-melody generation is an important task in automatic songwriting. Previous lyric-to-melody generation systems usually adopt end-to-end models that directly generate melodies from lyrics, which suffer from several issues: 1) lack of paired lyric-melody training data; 2) lack of control on generated melodies. In this paper, we develop TeleMelody, a two-stage lyric-to-melody generation system with music template (e.g., tonality, chord progression, rhythm pattern, and cadence) to bridge the gap between lyrics and melodies (i.e., the system consists of a lyric-to-template module and a templ…
JOHANNES KEPLER UNIVERSITY LINZ（约翰内斯·开普勒大学林茨分校）；Institute of Computational Perception（计算感知研究所）
In recent years, artificial neural networks (ANNs) have become a universal tool for tackling real-world problems. ANNs have also shown great success in music-related tasks including music summarization and classification, similarity estimation, computer-aided or autonomous composition, and automatic music analysis. As structure is a fundamental characteristic of Western music, it plays a role in all these tasks. Some structural aspects are particularly challenging to learn with current ANN architectures. This is especially true for mid- and high-level self-similarity, tonal and rhythmic relati…
We propose a novel system that takes as an input body movements of a musician playing a musical instrument and generates music in an unsupervised setting. Learning to generate multi-instrumental music from videos without labeling the instruments is a challenging problem. To achieve the transformation, we built a pipeline named 'Multi-instrumentalistNet' (MI Net). At its base, the pipeline learns a discrete latent representation of various instruments music from log-spectrogram using a Vector Quantized Variational Autoencoder (VQ-VAE) with multi-band residual blocks. The pipeline is then traine…
Microsoft Research Asia（微软亚洲研究院）；Dalian University of Technology（大连理工大学）；Zhejiang University（浙江大学）；Shanghai Jiao Tong University（上海交通大学）；Nanjing University（南京大学）
CompLex: Music Theory Lexicon Constructed by Autonomous Agents for Automatic Music Generation
Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算机系）；Zhejiang University-University of Illinois Urbana-Champaign Institute（浙江大学-伊利诺伊大学厄巴纳-香槟分校联合研究所）
Austrian Research Institute for Artificial Intelligence（奥地利人工智能研究所）；Johannes Kepler University（约翰内斯·开普勒大学）
We introduce a method for imposing higher-level structure on generated, polyphonic music. A Convolutional Restricted Boltzmann Machine (C-RBM) as a generative model is combined with gradient descent constraint optimisation to provide further control over the generation process. Among other things, this allows for the use of a "template" piece, from which some structural properties can be extracted, and transferred as constraints to the newly generated material. The sampling process is guided with Simulated Annealing to avoid local optima, and to find solutions that both satisfy the constraints…
University of Texas at Dallas（德克萨斯大学达拉斯分校）；University of Seville（塞维利亚大学）
The term melodic template or skeleton refers to a basic melody which is subject to variation during a music performance. In many oral music tradition, these templates are implicitly passed throughout generations without ever being formalized in a score. In this work, we introduce a new geometric optimization problem, the spanning tube problem, to approximate a melodic template for a set of labeled performance transcriptions corresponding to an specific style in oral music traditions. Given a set of $n$ piecewise linear functions, we solve the problem of finding a continuous function, $f^*$, an…
In this paper, we propose a novel neural network model called KaraSinger for a less-studied singing voice synthesis (SVS) task named score-free SVS, in which the prosody and melody are spontaneously decided by machine. KaraSinger comprises a vector-quantized variational autoencoder (VQ-VAE) that compresses the Mel-spectrograms of singing audio to sequences of discrete codes, and a language model (LM) that learns to predict the discrete codes given the corresponding lyrics. For the VQ-VAE part, we employ a Connectionist Temporal Classification (CTC) loss to encourage the discrete codes to carry…
Korea University（高丽大学）；Queen Mary University of London（伦敦玛丽女王大学）；Korea National Open University（韩国国立开放大学）
In recent years, neural network based methods have been proposed as a method that cangenerate representations from music, but they are not human readable and hardly analyzable oreditable by a human. To address this issue, we propose a novel method to learn source-awarelatent representations of music through Vector-Quantized Variational Auto-Encoder(VQ-VAE).We train our VQ-VAE to encode an input mixture into a tensor of integers in a discrete latentspace, and design them to have a decomposed structure which allows humans to manipulatethe latent vector in a source-aware manner. This paper also s…
A music piece is both comprehended hierarchically, from sonic events to melodies, and sequentially, in the form of repetition and variation. Music from different cultures establish different aesthetics by having different style conventions on these two aspects. We propose a framework that could be used to quantitatively compare music from different cultures by looking at these two aspects. The framework is based on an Music Information Dynamics model, a Variable Markov Oracle (VMO), and is extended with a variational representation learning of audio. A variational autoencoder (VAE) is trained …
Driving 3D characters to dance following a piece of music is highly challenging due to the spatial constraints applied to poses by choreography norms. In addition, the generated dance sequence also needs to maintain temporal coherency with different music genres. To tackle these challenges, we propose a novel music-to-dance framework, Bailando, with two powerful components: 1) a choreographic memory that learns to summarize meaningful dancing units from 3D pose sequence to a quantized codebook, 2) an actor-critic Generative Pre-trained Transformer (GPT) that composes these units to a fluent da…
Sony Computer Science Laboratory（索尼计算机科学实验室）；LTCI, Télécom Paris, Institut Polytechnique de Paris（LTCI，巴黎电信学院，巴黎综合理工学院）
Influenced by the field of Computer Vision, Generative Adversarial Networks (GANs) are often adopted for the audio domain using fixed-size two-dimensional spectrogram representations as the "image data". However, in the (musical) audio domain, it is often desired to generate output of variable duration. This paper presents VQCPC-GAN, an adversarial framework for synthesizing variable-length audio by exploiting Vector-Quantized Contrastive Predictive Coding (VQCPC). A sequence of VQCPC tokens extracted from real audio data serves as conditional input to a GAN architecture, providing step-wise t…
Creating a good drum track to imitate a skilled performer in digital audio workstations (DAWs) can be a time-consuming process, especially for those unfamiliar with drums. In this work, we introduce PocketVAE, a groove generation system that applies grooves to users' rudimentary MIDI tracks, i.e, templates. Grooves can be either transferred from a reference track, generated randomly or with conditions, such as genres. Our system, consisting of different modules for each groove component, takes a two-step approach that is analogous to a music creation process. First, the note module updates the…
