Related papers: Checklist Models for Improved Output Fluency in Pi…
This paper introduces the first system for performing automatic orchestration based on a real-time piano input. We believe that it is possible to learn the underlying regularities existing between piano scores and their orchestrations by…
Mastering dexterous manipulation with multi-fingered hands has been a grand challenge in robotics for decades. Despite its potential, the difficulty of collecting high-quality data remains a primary bottleneck for high-precision tasks.…
Audio-driven bimanual piano motion generation requires precise modeling of complex musical structures and dynamic cross-hand coordination. However, existing methods often rely on acoustic-only representations lacking symbolic priors, employ…
We propose modifications to the model structure and training procedure to a recently introduced Convolutional Neural Network for musical key classification. These modifications enable the network to learn a genre-independent model that…
Computational harmony analysis is important for MIR tasks such as automatic segmentation, corpus analysis and automatic chord label estimation. However, recent research into the ambiguous nature of musical harmony, causing limited…
The violin is one of the most popular musical instruments. Various parameters of bowing motion, such as pressure, position, and speed, are crucial for producing a beautiful tone. However, mastering them is challenging and requires extensive…
Workers spend a significant amount of time learning how to make good decisions. Evaluating the efficacy of a given decision, however, can be complicated -- e.g., decision outcomes are often long-term and relate to the original decision in…
A great number of deep learning based models have been recently proposed for automatic music composition. Among these models, the Transformer stands out as a prominent approach for generating expressive classical piano performance with a…
The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values. Reinforcement learning…
Preference-based learning of reward functions, where the reward function is learned using comparison data, has been well studied for complex robotic tasks such as autonomous driving. Existing algorithms have focused on learning reward…
Efficiently allocating incoming jobs to nodes in large-scale clusters can lead to substantial improvements in both cluster utilization and job performance. In order to allocate incoming jobs, cluster schedulers usually rely on a set of…
This paper investigates automatic piano transcription based on computationally-efficient yet high-performant variants of the Transformer that can capture longer-term dependency over the whole musical piece. Recently, transformer-based…
Current music recommender systems typically act in a greedy fashion by recommending songs with the highest user ratings. Greedy recommendation, however, is suboptimal over the long term: it does not actively gather information on user…
Piano cover generation aims to create a piano cover from a pop song. Existing approaches mainly employ supervised learning and the training demands strongly-aligned and paired song-to-piano data, which is built by remapping piano notes to…
Reinforcement learning is a general method for learning in sequential settings, but it can often be difficult to specify a good reward function when the task is complex. In these cases, preference feedback or expert demonstrations can be…
This paper addresses the weak instruments problem in linear instrumental variable models from a Bayesian perspective. The new approach has two components. First, a novel predictor-dependent shrinkage prior is developed for the many…
Current models for audio--sheet music retrieval via multimodal embedding space learning use convolutional neural networks with a fixed-size window for the input audio. Depending on the tempo of a query performance, this window captures more…
The task of estimating the gradient of a function in the presence of noise is central to several forms of reinforcement learning, including policy search methods. We present two techniques for reducing gradient estimation errors in the…
The popularity of applying machine learning techniques in musical domains has created an inherent availability of freely accessible pre-trained neural network (NN) models ready for use in creative applications. This work outlines the…
Music can be represented in multiple forms, such as in the audio form as a recording of a performance, in the symbolic form as a computer readable score, or in the image form as a scan of the sheet music. Music synchronisation provides a…