Digital advances have transformed the face of automatic music generation since its beginnings at the dawn of computing. Despite the many breakthroughs, issues such as the musical tasks targeted by different machines and the degree to which they succeed remain open questions. We present a functional taxonomy for music generation systems with reference to existing systems. The taxonomy organizes systems according to the purposes for which they were designed. It also reveals the inter-relatedness amongst the systems. This design-centered approach contrasts with predominant methods-based surveys and facilitates the identification of grand challenges to set the stage for new breakthroughs.
In this work, we define a diffusion-based generative model capable of both music synthesis and source separation by learning the score of the joint probability density of sources sharing a context. Alongside the classic total inference tasks (i.e. generating a mixture, separating the sources), we also introduce and experiment on the partial inference task of source imputation, where we generate a subset of the sources given the others (e.g., play a piano track that goes well with the drums). Additionally, we introduce a novel inference method for the separation task. We train our model on Slakh2100, a standard dataset for musical source separation, provide qualitative results in the generation settings, and showcase competitive quantitative results in the separation setting. Our method is the first example of a single model that can handle both generation and separation tasks, thus representing a step toward general audio models.
Generative audio models typically focus their applications in music and speech generation, with recent models having human-like quality in their audio output. This paper conducts a systematic literature review of 884 papers in the area of generative audio models in order to both quantify the degree to which researchers in the field are considering potential negative impacts and identify the types of ethical implications researchers in this area need to consider. Though 65% of generative audio research papers note positive potential impacts of their work, less than 10% discuss any negative impacts. This jarringly small percentage of papers considering negative impact is particularly worrying because the issues brought to light by the few papers doing so are raising serious ethical implications and concerns relevant to the broader field such as the potential for fraud, deep-fakes, and copyright infringement. By quantifying this lack of ethical consideration in generative audio research and identifying key areas of potential harm, this paper lays the groundwork for future work in the field at a critical point in time in order to guide more conscientious research as this field progresses.
Symbolic Music Generation relies on the contextual representation capabilities of the generative model, where the most prevalent approach is the Transformer-based model. Not only that, the learning of long-term context is also related to the dynamic segmentation of musical structures, i.e. intro, verse and chorus, which is currently overlooked by the research community. In this paper, we propose a multi-scale Transformer, which uses coarse-decoder and fine-decoders to model the contexts at the global and section-level, respectively. Concretely, we designed a Fragment Scope Localization layer to syncopate the music into sections, which were later used to pre-train fine-decoders. After that, we designed a Music Style Normalization layer to transfer the style information from the original sections to the generated sections to achieve consistency in music style. The generated sections are combined in the aggregation layer and fine-tuned by the coarse decoder. Our model is evaluated on two open MIDI datasets, and experiments show that our model outperforms the best contemporary symbolic music generative models. More excitingly, visual evaluation shows that our model is superior in melody reuse, resulting in more realistic music.
Despite their impressive offline results, deep learning models for symbolic music generation are not widely used in live performances due to a deficit of musically meaningful control parameters and a lack of structured musical form in their outputs. To address these issues we introduce LooperGP, a method for steering a Transformer-XL model towards generating loopable musical phrases of a specified number of bars and time signature, enabling a tool for live coding performances. We show that by training LooperGP on a dataset of 93,681 musical loops extracted from the DadaGP dataset, we are able to steer its generative output towards generating 3x as many loopable phrases as our baseline. In a subjective listening test conducted by 31 participants, LooperGP loops achieved positive median ratings in originality, musical coherence and loop smoothness, demonstrating its potential as a performance tool.
Launchpad is a musical instrument that allows users to create and perform music by pressing illuminated buttons. To assist and inspire the design of the Launchpad light effect, and provide a more accessible approach for beginners to create music visualization with this instrument, we proposed the LaunchpadGPT model to generate music visualization designs on Launchpad automatically. Based on the language model with excellent generation ability, our proposed LaunchpadGPT takes an audio piece of music as input and outputs the lighting effects of Launchpad-playing in the form of a video (Launchpad-playing video). We collect Launchpad-playing videos and process them to obtain music and corresponding video frame of Launchpad-playing as prompt-completion pairs, to train the language model. The experiment result shows the proposed method can create better music visualization than random generation methods and hold the potential for a broader range of music visualization applications. Our code is available at https://github.com/yunlong10/LaunchpadGPT/.
Attention-based Transformer models have been increasingly employed for automatic music generation. To condition the generation process of such a model with a user-specified sequence, a popular approach is to take that conditioning sequence as a priming sequence and ask a Transformer decoder to generate a continuation. However, this prompt-based conditioning cannot guarantee that the conditioning sequence would develop or even simply repeat itself in the generated continuation. In this paper, we propose an alternative conditioning approach, called theme-based conditioning, that explicitly trains the Transformer to treat the conditioning sequence as a thematic material that has to manifest itself multiple times in its generation result. This is achieved with two main technical contributions. First, we propose a deep learning-based approach that uses contrastive representation learning and clustering to automatically retrieve thematic materials from music pieces in the training data. Second, we propose a novel gated parallel attention module to be used in a sequence-to-sequence (seq2seq) encoder/decoder architecture to more effectively account for a given conditioning thematic material in the generation process of the Transformer decoder. We report on objective and subjective evaluations of variants of the proposed Theme Transformer and the conventional prompt-based baseline, showing that our best model can generate, to some extent, polyphonic pop piano music with repetition and plausible variations of a given condition.
We propose a novel task for generating 3D dance movements that simultaneously incorporate both text and music modalities. Unlike existing works that generate dance movements using a single modality such as music, our goal is to produce richer dance movements guided by the instructive information provided by the text. However, the lack of paired motion data with both music and text modalities limits the ability to generate dance movements that integrate both. To alleviate this challenge, we propose to utilize a 3D human motion VQ-VAE to project the motions of the two datasets into a latent space consisting of quantized vectors, which effectively mix the motion tokens from the two datasets with different distributions for training. Additionally, we propose a cross-modal transformer to integrate text instructions into motion generation architecture for generating 3D dance movements without degrading the performance of music-conditioned dance generation. To better evaluate the quality of the generated motion, we introduce two novel metrics, namely Motion Prediction Distance (MPD) and Freezing Score, to measure the coherence and freezing percentage of the generated motion. Extensive experiments show that our approach can generate realistic and coherent dance movements conditioned on both text and music while maintaining comparable performance with the two single modalities. Code will be available at: https://garfield-kh.github.io/TM2D/.
Despite significant advances in deep models for music generation, the use of these techniques remains restricted to expert users. Before being democratized among musicians, generative models must first provide expressive control over the generation, as this conditions the integration of deep generative models in creative workflows. In this paper, we tackle this issue by introducing a deep generative audio model providing expressive and continuous descriptor-based control, while remaining lightweight enough to be embedded in a hardware synthesizer. We enforce the controllability of real-time generation by explicitly removing salient musical features in the latent space using an adversarial confusion criterion. User-specified features are then reintroduced as additional conditioning information, allowing for continuous control of the generation, akin to a synthesizer knob. We assess the performance of our method on a wide variety of sounds including instrumental, percussive and speech recordings while providing both timbre and attributes transfer, allowing new ways of generating sounds.