Neural style transfer, allowing to apply the artistic style of one image to another, has become one of the most widely showcased computer vision applications shortly after its introduction. In contrast, related tasks in the music audio domain remained, until recently, largely untackled. While several style conversion methods tailored to musical signals have been proposed, most lack the 'one-shot' capability of classical image style transfer algorithms. On the other hand, the results of existing one-shot audio style transfer methods on musical inputs are not as compelling. In this work, we are specifically interested in the problem of one-shot timbre transfer. We present a novel method for this task, based on an extension of the vector-quantized variational autoencoder (VQ-VAE), along with a simple self-supervised learning strategy designed to obtain disentangled representations of timbre and pitch. We evaluate the method using a set of objective metrics and show that it is able to outperform selected baselines.
We introduce MIDI-VAE, a neural network model based on Variational Autoencoders that is capable of handling polyphonic music with multiple instrument tracks, as well as modeling the dynamics of music by incorporating note durations and velocities. We show that MIDI-VAE can perform style transfer on symbolic music by automatically changing pitches, dynamics and instruments of a music piece from, e.g., a Classical to a Jazz style. We evaluate the efficacy of the style transfer by training separate style validation classifiers. Our model can also interpolate between short pieces of music, produce…
University of Science and Technology of China（中国科学技术大学）
Currently, almost all the multi-track music generation models use the Convolutional Neural Network (CNN) to build the generative model, while the Recurrent Neural Network (RNN) based models can not be applied in this task. In view of the above problem, this paper proposes a RNN-based Hierarchical Multi-modal Fusion Generation Variational Autoencoder (VAE) network, MIDI-Sandwich2, for multi-track symbolic music generation. Inspired by VQ-VAE2, MIDI-Sandwich2 expands the dimension of the original hierarchical model by using multiple independent Binary Variational Autoencoder (BVAE) models withou…
The Variational Autoencoder (VAE) has proven to be an effective model for producing semantically meaningful latent representations for natural data. However, it has thus far seen limited application to sequential data, and, as we demonstrate, existing recurrent VAE models have difficulty modeling sequences with long-term structure. To address this issue, we propose the use of a hierarchical decoder, which first outputs embeddings for subsequences of the input and then uses these embeddings to generate each subsequence independently. This structure encourages the model to utilize its latent cod…
Center for the Neural Basis of Cognition, Machine Learning Department（认知神经基础中心，机器学习系）；Carnegie Mellon University（卡内基梅隆大学）
The variational autoencoder (VAE) is a popular probabilistic generative model. However, one shortcoming of VAEs is that the latent variables cannot be discrete, which makes it difficult to generate data from different modes of a distribution. Here, we propose an extension of the VAE framework that incorporates a classifier to infer the discrete class of the modeled data. To model sequential data, we can combine our Classifying VAE with a recurrent neural network such as an LSTM. We apply this model to algorithmic music generation, where our model learns to generate musical sequences in differe…
Variational Autoencoders(VAEs) have already achieved great results on image generation and recently made promising progress on music generation. However, the generation process is still quite difficult to control in the sense that the learned latent representations lack meaningful music semantics. It would be much more useful if people can modify certain music features, such as rhythm and pitch contour, via latent representations to test different composition ideas. In this paper, we propose a new method to inspect the pitch and rhythm interpretations of the latent representations and we name …
University of Science and Technology of China（中国科学技术大学）
Most existing neural network models for music generation explore how to generate music bars, then directly splice the music bars into a song. However, these methods do not explore the relationship between the bars, and the connected song as a whole has no musical form structure and sense of musical direction. To address this issue, we propose a Multi-model Multi-task Hierarchical Conditional VAE-GAN (Variational Autoencoder-Generative adversarial networks) networks, named MIDI-Sandwich, which combines musical knowledge, such as musical form, tonic, and melodic motion. The MIDI-Sandwich has two…
Taiwan AI Labs（台湾人工智能实验室）；National Taiwan University（台湾大学）；Academia Sinica（中央研究院）
Transformers and variational autoencoders (VAE) have been extensively employed for symbolic (e.g., MIDI) domain music generation. While the former boast an impressive capability in modeling long sequences, the latter allow users to willingly exert control over different parts (e.g., bars) of the music to be generated. In this paper, we are interested in bringing the two together to construct a single model that exhibits both strengths. The task is split into two steps. First, we equip Transformer decoders with the ability to accept segment-level, time-varying conditions during sequence generat…
Deep generative models such as Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) have recently been applied to style and domain transfer for images, and in the case of VAEs, music. GAN-based models employing several generators and some form of cycle consistency loss have been among the most successful for image domain transfer. In this paper we apply such a model to symbolic music and show the feasibility of our approach for music genre transfer. Evaluations using separate genre classifiers show that the style transfer works well. In order to improve the fidelity of th…
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…
In this paper we explore techniques for generating new music using a Variational Autoencoder (VAE) neural network that was trained on a corpus of specific style. Instead of randomly sampling the latent states of the network to produce free improvisation, we generate new music by querying the network with musical input in a style different from the training corpus. This allows us to produce new musical output with longer-term structure that blends aspects of the query to the style of the network. In order to control the level of this blending we add a noisy channel between the VAE encoder and d…
Centro de investigación CITIC（CITIC研究中心）；University of A Coruña（拉科鲁尼亚大学）
This paper proposes a new model for music prediction based on Variational Autoencoders (VAEs). In this work, VAEs are used in a novel way in order to address two different problems: music representation into the latent space, and using this representation to make predictions of the future values of the musical piece. This approach was trained with different songs of a classical composer. As a result, the system can represent the music in the latent space, and make accurate predictions. Therefore, the system can be used to compose new music either from an existing piece or from a random startin…
We address the challenging open problem of learning an effective latent space for symbolic music data in generative music modeling. We focus on leveraging adversarial regularization as a flexible and natural mean to imbue variational autoencoders with context information concerning music genre and style. Through the paper, we show how Gaussian mixtures taking into account music metadata information can be used as an effective prior for the autoencoder latent space, introducing the first Music Adversarial Autoencoder (MusAE). The empirical analysis on a large scale benchmark shows that our mode…
We propose a Text-to-Speech method to create an unseen expressive style using one utterance of expressive speech of around one second. Specifically, we enhance the disentanglement capabilities of a state-of-the-art sequence-to-sequence based system with a Variational AutoEncoder (VAE) and a Householder Flow. The proposed system provides a 22% KL-divergence reduction while jointly improving perceptual metrics over state-of-the-art. At synthesis time we use one example of expressive style as a reference input to the encoder for generating any text in the desired style. Perceptual MUSHRA evaluati…
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 …
Volkswagen Group（大众集团）；ArgoAI；St. Pölten University of Applied Sciences（圣帕尔滕应用科学大学）；St Joost School of Art and Design（圣约斯特艺术与设计学院）
The use of machine learning in artistic music generation leads to controversial discussions of the quality of art, for which objective quantification is nonsensical. We therefore consider a music-generating algorithm as a counterpart to a human musician, in a setting where reciprocal interplay is to lead to new experiences, both for the musician and the audience. To obtain this behaviour, we resort to the framework of recurrent Variational Auto-Encoders (VAE) and learn to generate music, seeded by a human musician. In the learned model, we generate novel musical sequences by interpolation in l…
There has been significant progress in the music generation technique utilizing deep learning. However, it is still hard for musicians and artists to use these techniques in their daily music-making practice. This paper proposes a Variational Autoencoder\cite{Kingma2014}(VAE)-based rhythm generation system, in which musicians can train a deep learning model only by selecting target MIDI files, then generate various rhythms with the model. The author has implemented the system as a plugin software for a DAW (Digital Audio Workstation), namely a Max for Live device for Ableton Live. Selected pro…
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…
This paper aims to disentangle the latent space in cVAE into the spatial structure and the style code, which are complementary to each other, with one of them $z_s$ being label relevant and the other $z_u$ irrelevant. The generator is built by a connected encoder-decoder and a label condition mapping network. Depending on whether the label is related with the spatial structure, the output $z_s$ from the condition mapping network is used either as a style code or a spatial structure code. The encoder provides the label irrelevant posterior from which $z_u$ is sampled. The decoder employs $z_s$ …
NYU Shanghai（纽约大学上海分校）；Carnegie Mellon University（卡内基梅隆大学）
Analogy-making is a key method for computer algorithms to generate both natural and creative music pieces. In general, an analogy is made by partially transferring the music abstractions, i.e., high-level representations and their relationships, from one piece to another; however, this procedure requires disentangling music representations, which usually takes little effort for musicians but is non-trivial for computers. Three sub-problems arise: extracting latent representations from the observation, disentangling the representations so that each part has a unique semantic interpretation, and…
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…
A semi-recurrent hybrid VAE-GAN model for generating sequential data is introduced. In order to consider the spatial correlation of the data in each frame of the generated sequence, CNNs are utilized in the encoder, generator, and discriminator. The subsequent frames are sampled from the latent distributions obtained by encoding the previous frames. As a result, the dependencies between the frames are maintained. Two testing frameworks for synthesizing a sequence with any number of frames are also proposed. The promising experimental results on piano music generation indicates the potential of…
Samsung AI Center Cambridge（三星人工智能中心剑桥）；Rutgers University（罗格斯大学）
In deep representational learning, it is often desired to isolate a particular factor (termed {\em content}) from other factors (referred to as {\em style}). What constitutes the content is typically specified by users through explicit labels in the data, while all unlabeled/unknown factors are regarded as style. Recently, it has been shown that such content-labeled data can be effectively exploited by modifying the deep latent factor models (e.g., VAE) such that the style and content are well separated in the latent representations. However, the approach assumes that the content factor is cat…
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…
Traditional voice conversion methods rely on parallel recordings of multiple speakers pronouncing the same sentences. For real-world applications however, parallel data is rarely available. We propose MelGAN-VC, a voice conversion method that relies on non-parallel speech data and is able to convert audio signals of arbitrary length from a source voice to a target voice. We firstly compute spectrograms from waveform data and then perform a domain translation using a Generative Adversarial Network (GAN) architecture. An additional siamese network helps preserving speech information in the trans…
rinna Co., Ltd.（Rinna株式会社）；Nagoya Institute of Technology（名古屋工业大学）
The recent text-to-speech (TTS) has achieved quality comparable to that of humans; however, its application in spoken dialogue has not been widely studied. This study aims to realize a TTS that closely resembles human dialogue. First, we record and transcribe actual spontaneous dialogues. Then, the proposed dialogue TTS is trained in two stages: first stage, variational autoencoder (VAE)-VITS or Gaussian mixture variational autoencoder (GMVAE)-VITS is trained, which introduces an utterance-level latent variable into variational inference with adversarial learning for end-to-end text-to-speech …
Université Pierre et Marie Curie（皮埃尔和玛丽·居里大学）；Sony CSL（索尼计算机科学研究所）；École Polytechnique（巴黎综合理工学院）
VAEs (Variational AutoEncoders) have proved to be powerful in the context of density modeling and have been used in a variety of contexts for creative purposes. In many settings, the data we model possesses continuous attributes that we would like to take into account at generation time. We propose in this paper GLSR-VAE, a Geodesic Latent Space Regularization for the Variational AutoEncoder architecture and its generalizations which allows a fine control on the embedding of the data into the latent space. When augmenting the VAE loss with this regularization, changes in the learned latent spa…
UC Santa Barbara（加州大学圣巴巴拉分校）；Lawrence Berkeley National Lab（劳伦斯伯克利国家实验室）
We summarize the model and results of PirouNet, a semi-supervised recurrent variational autoencoder. Given a small amount of dance sequences labeled with qualitative choreographic annotations, PirouNet conditionally generates dance sequences in the style of the choreographer.
Automatic music generation is an interdisciplinary research topic that combines computational creativity and semantic analysis of music to create automatic machine improvisations. An important property of such a system is allowing the user to specify conditions and desired properties of the generated music. In this paper we designed a model for composing melodies given a user specified symbolic scenario combined with a previous music context. We add manual labeled vectors denoting external music quality in terms of chord function that provides a low dimensional representation of the harmonic t…
NYU Shanghai（纽约大学上海分校）；New York University（纽约大学）；Zhejiang University（浙江大学）
The dominant approach for music representation learning involves the deep unsupervised model family variational autoencoder (VAE). However, most, if not all, viable attempts on this problem have largely been limited to monophonic music. Normally composed of richer modality and more complex musical structures, the polyphonic counterpart has yet to be addressed in the context of music representation learning. In this work, we propose the PianoTree VAE, a novel tree-structure extension upon VAE aiming to fit the polyphonic music learning. The experiments prove the validity of the PianoTree VAE vi…
Automatic melody generation has been a long-time aspiration for both AI researchers and musicians. However, learning to generate euphonious melodies has turned out to be highly challenging. This paper introduces 1) a new variant of variational autoencoder (VAE), where the model structure is designed in a modularized manner in order to model polyphonic and dynamic music with domain knowledge, and 2) a hierarchical encoding/decoding strategy, which explicitly models the dependency between melodic features. The proposed framework is capable of generating distinct melodies that sounds natural, and…
Machine learning has had a great deal of success in image processing. However, the focus of this work has largely been on realistic images, ignoring more niche art styles such as pixel art. Additionally, many traditional machine learning models that focus on groups of pixels do not work well with pixel art, where individual pixels are important. We propose the Pixel VQ-VAE, a specialized VQ-VAE model that learns representations of pixel art. We show that it outperforms other models in both the quality of embeddings as well as performance on downstream tasks.
Music is a repetition of patterns and rhythms. It can be composed by repeating a certain number of bars in a structured way. In this paper, the objective is to generate a loop of 8 bars that can be used as a building block of music. Even considering musical diversity, we assume that music patterns familiar to humans can be defined in a finite set. With explicit rules to extract loops from music, we found that discrete representations are sufficient to model symbolic music sequences. Among VAE family, musical properties from VQ-VAE are better observed rather than other models. Further, to empha…
Télécom Paris（巴黎电信学院）；Institut Polytechnique de Paris（巴黎综合理工学院）
Research on style transfer and domain translation has clearly demonstrated the ability of deep learning-based algorithms to manipulate images in terms of artistic style. More recently, several attempts have been made to extend such approaches to music (both symbolic and audio) in order to enable transforming musical style in a similar manner. In this study, we focus on symbolic music with the goal of altering the 'style' of a piece while keeping its original 'content'. As opposed to the current methods, which are inherently restricted to be unsupervised due to the lack of 'aligned' data (i.e. …
Regional style in Chinese folk songs is a rich treasure that can be used for ethnic music creation and folk culture research. In this paper, we propose MG-VAE, a music generative model based on VAE (Variational Auto-Encoder) that is capable of capturing specific music style and generating novel tunes for Chinese folk songs (Min Ge) in a manipulatable way. Specifically, we disentangle the latent space of VAE into four parts in an adversarial training way to control the information of pitch and rhythm sequence, as well as of music style and content. In detail, two classifiers are used to separat…
We consider the problem of learning high-level controls over the global structure of generated sequences, particularly in the context of symbolic music generation with complex language models. In this work, we present the Transformer autoencoder, which aggregates encodings of the input data across time to obtain a global representation of style from a given performance. We show it is possible to combine this global representation with other temporally distributed embeddings, enabling improved control over the separate aspects of performance style and melody. Empirically, we demonstrate the eff…
T-Brain X；SK Telecom（SK电讯）；Graduate School of Culture Technology（文化技术研究生院）；KAIST（韩国科学技术院）
The goal of this paper to generate a visually appealing video that responds to music with a neural network so that each frame of the video reflects the musical characteristics of the corresponding audio clip. To achieve the goal, we propose a neural music visualizer directly mapping deep music embeddings to style embeddings of StyleGAN, named TräumerAI, which consists of a music auto-tagging model using short-chunk CNN and StyleGAN2 pre-trained on WikiArt dataset. Rather than establishing an objective metric between musical and visual semantics, we manually labeled the pairs in a subjective ma…
Modelling human perception of musical similarity is critical for the evaluation of generative music systems, musicological research, and many Music Information Retrieval tasks. Although human similarity judgments are the gold standard, computational analysis is often preferable, since results are often easier to reproduce, and computational methods are much more scalable. Moreover, computation based approaches can be calculated quickly and on demand, which is a prerequisite for use with an online system. We propose StyleRank, a method to measure the similarity between a MIDI file and an arbitr…
Peking University（北京大学）；New York University Shanghai（上海纽约大学）
Led by the success of neural style transfer on visual arts, there has been a rising trend very recently in the effort of music style transfer. However, "music style" is not yet a well-defined concept from a scientific point of view. The difficulty lies in the intrinsic multi-level and multi-modal character of music representation (which is very different from image representation). As a result, depending on their interpretation of "music style", current studies under the category of "music style transfer", are actually solving completely different problems that belong to a variety of sub-field…
Deep generative systems that learn probabilistic models from a corpus of existing music do not explicitly encode knowledge of a musical style, compared to traditional rule-based systems. Thus, it can be difficult to determine whether deep models generate stylistically correct output without expert evaluation, but this is expensive and time-consuming. Therefore, there is a need for automatic, interpretable, and musically-motivated evaluation measures of generated music. In this paper, we introduce a grading function that evaluates four-part chorales in the style of J.S. Bach along important mus…
Computer Science and Engineering University of California, San Diego（加利福尼亚大学圣地亚哥分校计算机科学与工程学院）
Recent advances in deep neural networks have enabled algorithms to compose music that is comparable to music composed by humans. However, few algorithms allow the user to generate music with tunable parameters. The ability to tune properties of generated music will yield more practical benefits for aiding artists, filmmakers, and composers in their creative tasks. In this paper, we introduce DeepJ - an end-to-end generative model that is capable of composing music conditioned on a specific mixture of composer styles. Our innovations include methods to learn musical style and music dynamics. We…
École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
Hand in hand with deep learning advancements, algorithms of music composition increase in performance. However, most of the successful models are designed for specific musical structures. Here, we present BachProp, an algorithmic composer that can generate music scores in any style given sufficient training data. To adapt BachProp to a broad range of musical styles, we propose a novel normalized representation of music and train a deep network to predict the note transition probabilities of a given music corpus. In this paper, new music scores sampled by BachProp are compared with the original…
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）
Cross-speaker style transfer in speech synthesis aims at transferring a style from source speaker to synthesised speech of a target speaker's timbre. Most previous approaches rely on data with style labels, but manually-annotated labels are expensive and not always reliable. In response to this problem, we propose Style-Label-Free, a cross-speaker style transfer method, which can realize the style transfer from source speaker to target speaker without style labels. Firstly, a reference encoder structure based on quantized variational autoencoder (Q-VAE) and style bottleneck is designed to extr…
