Music tagging and content-based retrieval systems have traditionally been constructed using pre-defined ontologies covering a rigid set of music attributes or text queries. This paper presents MuLan: a first attempt at a new generation of acoustic models that link music audio directly to unconstrained natural language music descriptions. MuLan takes the form of a two-tower, joint audio-text embedding model trained using 44 million music recordings (370K hours) and weakly-associated, free-form text annotations. Through its compatibility with a wide range of music genres and text styles (including conventional music tags), the resulting audio-text representation subsumes existing ontologies while graduating to true zero-shot functionalities. We demonstrate the versatility of the MuLan embeddings with a range of experiments including transfer learning, zero-shot music tagging, language understanding in the music domain, and cross-modal retrieval applications.
Assessing perceptual quality of musical audio signals usually requires a clean reference signal of unaltered content, hindering applications where a reference is unavailable such as for music generation. We propose training a generative adversarial network on a music library, and using its discriminator as a measure of the perceived quality of music. This method is unsupervised, needs no access to degraded material and can be tuned for various domains of music. Finally, the method is shown to have a statistically significant correlation with human ratings of music.
Dance choreography for a piece of music is a challenging task, having to be creative in presenting distinctive stylistic dance elements while taking into account the musical theme and rhythm. It has been tackled by different approaches such as similarity retrieval, sequence-to-sequence modeling and generative adversarial networks, but their generated dance sequences are often short of motion realism, diversity and music consistency. In this paper, we propose a Music-to-Dance with Optimal Transport Network (MDOT-Net) for learning to generate 3D dance choreographs from music. We introduce an optimal transport distance for evaluating the authenticity of the generated dance distribution and a Gromov-Wasserstein distance to measure the correspondence between the dance distribution and the input music. This gives a well defined and non-divergent training objective that mitigates the limitation of standard GAN training which is frequently plagued with instability and divergent generator loss issues. Extensive experiments demonstrate that our MDOT-Net can synthesize realistic and diverse dances which achieve an organic unity with the input music, reflecting the shared intentionality and matching the rhythmic articulation.
Since the introduction of deep learning, researchers have proposed content generation systems using deep learning and proved that they are competent to generate convincing content and artistic output, including music. However, one can argue that these deep learning-based systems imitate and reproduce the patterns inherent within what humans have created, instead of generating something new and creative. This paper focuses on music generation, especially rhythm patterns of electronic dance music, and discusses if we can use deep learning to generate novel rhythms, interesting patterns not found in the training dataset. We extend the framework of Generative Adversarial Networks(GAN) and encourage it to diverge from the dataset's inherent distributions by adding additional classifiers to the framework. The paper shows that our proposed GAN can generate rhythm patterns that sound like music rhythms but do not belong to any genres in the training dataset. The source code, generated rhythm patterns, and a supplementary plugin software for a popular Digital Audio Workstation software are available on our website.
We present a deep convolutional GAN which leverages techniques from MP3/Vorbis audio compression to produce long, high-quality audio samples with long-range coherence. The model uses a Modified Discrete Cosine Transform (MDCT) data representation, which includes all phase information. Phase generation is hence integral part of the model. We leverage the auditory masking and psychoacoustic perception limit of the human ear to widen the true distribution and stabilize the training process. The model architecture is a deep 2D convolutional network, where each subsequent generator model block increases the resolution along the time axis and adds a higher octave along the frequency axis. The deeper layers are connected with all parts of the output and have the context of the full track. This enables generation of samples which exhibit long-range coherence. We use MP3net to create 95s stereo tracks with a 22kHz sample rate after training for 250h on a single Cloud TPUv2. An additional benefit of the CNN-based model architecture is that generation of new songs is almost instantaneous.
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.
There is a growing desire to create computer systems that can communicate effectively to collaborate with humans on complex, open-ended activities. Assessing these systems presents significant challenges. We describe a framework for evaluating systems engaged in open-ended complex scenarios where evaluators do not have the luxury of comparing performance to a single right answer. This framework has been used to evaluate human-machine creative collaborations across story and music generation, interactive block building, and exploration of molecular mechanisms in cancer. These activities are fundamentally different from the more constrained tasks performed by most contemporary personal assistants as they are generally open-ended, with no single correct solution, and often no obvious completion criteria. We identified the Key Properties that must be exhibited by successful systems. From there we identified "Hallmarks" of success -- capabilities and features that evaluators can observe that would be indicative of progress toward achieving a Key Property. In addition to being a framework for assessment, the Key Properties and Hallmarks are intended to serve as goals in guiding research direction.
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 via (i)-semantically meaningful latent code for polyphonic segments; (ii)-more satisfiable reconstruction aside of decent geometry learned in the latent space; (iii)-this model's benefits to the variety of the downstream music generation.
We present a fast and high-fidelity method for music generation, based on specified f0 and loudness, such that the synthesized audio mimics the timbre and articulation of a target instrument. The generation process consists of learned source-filtering networks, which reconstruct the signal at increasing resolutions. The model optimizes a multi-resolution spectral loss as the reconstruction loss, an adversarial loss to make the audio sound more realistic, and a perceptual f0 loss to align the output to the desired input pitch contour. The proposed architecture enables high-quality fitting of an instrument, given a sample that can be as short as a few minutes, and the method demonstrates state-of-the-art timbre transfer capabilities. Code and audio samples are shared at https://github.com/mosheman5/timbre_painting.
The two main research threads in computer-based music generation are: the construction of autonomous music-making systems, and the design of computer-based environments to assist musicians. In the symbolic domain, the key problem of automatically arranging a piece music was extensively studied, while relatively fewer systems tackled this challenge in the audio domain. In this contribution, we propose CycleDRUMS, a novel method for generating drums given a bass line. After converting the waveform of the bass into a mel-spectrogram, we are able to automatically generate original drums that follow the beat, sound credible and can be directly mixed with the input bass. We formulated this task as an unpaired image-to-image translation problem, and we addressed it with CycleGAN, a well-established unsupervised style transfer framework, originally designed for treating images. The choice to deploy raw audio and mel-spectrograms enabled us to better represent how humans perceive music, and to potentially draw sounds for new arrangements from the vast collection of music recordings accumulated in the last century. In absence of an objective way of evaluating the output of both generative adversarial networks and music generative systems, we further defined a possible metric for the proposed task, partially based on human (and expert) judgement. Finally, as a comparison, we replicated our results with Pix2Pix, a paired image-to-image translation network, and we showed that our approach outperforms it.