This paper describes a neural music arrangement method that converts a given band score into a piano score with an elementary or advanced level. The major challenge of this task lies in its ill-posed nature, i.e., various piano arrangements are plausible for a band score. In this paper, we take a score reduction approach based on supervised training of a mask estimation network (U-Net) with note- and statistic-level criteria. Based on statistical analysis of existing piano arrangements, a reasonable piano score is assumed to be obtained by reducing an augmented band score obtained by up- and downshifting an original band score by one octave. This effectively narrows down a solution space. At the heart of our approach is to train a U-Net conditioned by a given difficulty level such that a piano score obtained by masking an augmented band score is close to the ground-truth piano score not only at a note level but also at a statistic level. We focus on three kinds of note statistics, i.e., a distribution of the numbers of concurrent notes, that of the intervals between the highest and lowest pitches, and that of the per-measure numbers of notes. The experimental results show the importance of both the instance- and meta-level criteria for supervised training.

This paper describes a statistically-principled semi-supervised method of automatic chord estimation (ACE) that can make effective use of music signals regardless of the availability of chord annotations. The typical approach to ACE is to train a deep classification model (neural chord estimator) in a supervised manner by using only annotated music signals. In this discriminative approach, prior knowledge about chord label sequences (model output) has scarcely been taken into account. In contrast, we propose a unified generative and discriminative approach in the framework of amortized variational inference. More specifically, we formulate a deep generative model that represents the generative process of chroma vectors (observed variables) from discrete labels and continuous features (latent variables), which are assumed to follow a Markov model favoring self-transitions and a standard Gaussian distribution, respectively. Given chroma vectors as observed data, the posterior distributions of the latent labels and features are computed approximately by using deep classification and recognition models, respectively. These three models form a variational autoencoder and can be trained jointly in a semi-supervised manner. The experimental results show that the regularization of the classification model based on the Markov prior of chord labels and the generative model of chroma vectors improved the performance of ACE even under the supervised condition. The semi-supervised learning using additional non-annotated data can further improve the performance.

With the advances of machine learning technologies, data-driven feature extraction and sequence modeling approaches are being widely explored for automatic chord recognition tasks. Currently, there is a bottleneck in the amount of enough annotated data for training robust acoustic models, as hand-annotating time-synchronized chord labels requires professional musical skills and considerable labor. To cope with this limitation, in this paper, we propose a convolutional neural network (CNN) based deep feature extractor, which is trained on a large set of time, synchronized musical instrument digital interface audio data pairs and can robustly estimate pitch class activations of real-world music audio recordings. The CNN feature extractor plus a bidirectional long short-term memory conditional random field decoding model forms the proposed hybrid system for automatic chord recognition. Experiments show that the proposed model is compatible for both regular major/minor triad chord classification and larger vocabulary chord recognition, and outperforms other state-of-the-art chord recognition systems.

In this paper, we design a novel deep learning based hybrid system for automatic chord recognition. Currently, there is a bottleneck in the amount of enough annotated data for training robust acoustic models, as hand annotating time-synchronized chord labels requires professional musical skills and considerable labor. As a solution to this problem, we construct a large set of time synchronized MIDI-audio pairs, and use these data to train a Deep Residual Network (DRN) feature extractor, which can then estimate pitch class activations of real-world music audio recordings. Sequence classification and decoding are then performed with a trained Bidirectional LSTM and Conditional Random Fields (CRF) network. Experiments show that the proposed model is compatible for both regular major/minor triad chord classification and larger vocabulary chord recognition, the performance is good and no less than other state-of-the-art systems. The proposed system also achieved good evaluation score in MIREX 2017 Automatic Chord Estimation task.