A BSTRACT We consider the problem of learning high-level controls over the global structure of sequence generation, particularly in the context of symbolic music generation with complex language models. In this work, we present the Transformer au-toencoder, 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 embedding with other temporally distributed embeddings, enabling improved control over the separate aspects of performance style and and melody. Empirically, we demonstrate the effectiveness of our method on a variety of music generation tasks on the MAESTRO dataset and a Y ouTube dataset with 10,000 hours of piano performances, where we achieve improvements in terms of log-likelihood and mean listening scores as compared to relevant baselines. As the number of generative applications increase, it becomes increasingly important to consider how users can interact with such systems, particularly when the generative model functions as a tool in their creative process (Engel et al., 2017a; Gillick et al., 2019) To this end, we consider how one can learn high-level controls over the global structure of a generated sample. We focus on symbolic music generation, where Music Transformer (Huang et al., 2019b) is the current state-of-the-art in generating high-quality samples that span over a minute in length. The challenge in controllable sequence generation is that Transformers (V aswani et al., 2017) and their variants excel as language models or in sequence-to-sequence tasks such as translation, but it is less clear as to how they can: (1) learn and (2) incorporate global conditioning information at inference time.
ABSTRACT The recent success of raw audio waveform synthesis models like WaveNet motivates a new approach for music synthesis, in which the entire process -- creating audio samples from a score and instrument information -- is modeled using generative neural networks. This paper describes a neural music synthesis model with flexible timbre controls, which consists of a recurrent neural network conditioned on a learned instrument embedding followed by a WaveNet vocoder. The learned embedding space successfully captures the diverse variations in timbres within a large dataset and enables timbre control and morphing by interpolating between instruments in the embedding space. The synthesis quality is evaluated both numerically and perceptually, and an interactive web demo is presented. Index Terms-- Music Synthesis, Timbre Embedding, WaveNet 1. INTRODUCTION Musical synthesis, most commonly, is the process of generating musical audio with given control parameters such as instrument type and note sequences over time.
We consider the problem of transcribing polyphonic piano music with an emphasis on generalizing to unseen instruments. We use deep neural networks and propose a novel approach that predicts onsets and frames using both CNNs and LSTMs. This model predicts pitch onset events and then uses those predictions to condition framewise pitch predictions. During inference, we restrict the predictions from the framewise detector by not allowing a new note to start unless the onset detector also agrees that an onset for that pitch is present in the frame. We focus on improving onsets and offsets together instead of either in isolation as we believe it correlates better with human musical perception. This technique results in over a 100% relative improvement in note with offset score on the MAPS dataset.
I started playing piano when I was five years old. I used to practice for about an hour every day and let me tell you, an hour felt like forever. I didn't stop thought, and I kept on practicing though, because I really liked music. Fast forward a few years and I started doing some really advanced stuff. My hands were literally flying all over the keyboard and I could play with my eyes closed.
We study the ability of Wasserstein Generative Adversarial Network (WGAN) to generate missing audio content which is, in context, (statistically similar) to the sound and the neighboring borders. We deal with the challenge of audio inpainting long range gaps (500 ms) using WGAN models. We improved the quality of the inpainting part using a new proposed WGAN architecture that uses a short-range and a long-range neighboring borders compared to the classical WGAN model. The performance was compared with two different audio instruments (piano and guitar) and on virtuoso pianists together with a string orchestra. The objective difference grading (ODG) was used to evaluate the performance of both architectures. The proposed model outperforms the classical WGAN model and improves the reconstruction of high-frequency content. Further, we got better results for instruments where the frequency spectrum is mainly in the lower range where small noises are less annoying for human ear and the inpainting part is more perceptible. Finally, we could show that better test results for audio dataset were reached where a particular instrument is accompanist by other instruments if we train the network only on this particular instrument neglecting the other instruments.