A Distributed Model For Multiple-Viewpoint Melodic Prediction

2015 International Joint Conference on Neural Networks (IJCNN), 2015

We are interested in modelling musical pitch sequences in melodies in the symbolic form. The task here is to learn a model to predict the probability distribution over the various possible values of pitch of the next note in a melody, given those leading up to it. For this task, we propose the Recurrent Temporal Discriminative Restricted Boltzmann Machine (RTDRBM). It is obtained by carrying out discriminative learning and inference as put forward in the Discriminative RBM (DRBM), in a temporal setting by incorporating the recurrent structure of the Recurrent Temporal RBM (RTRBM). The model is evaluated on the cross entropy of its predictions using a corpus containing 8 datasets of folk and chorale melodies, and compared with n-grams and other standard connectionist models. Results show that the RTDRBM has a better predictive performance than the rest of the models, and that the improvement is statistically significant.

Lecture Notes in Computer Science, 2011

Modelling the real world complexity of music is a challenge for machine learning. We address the task of modeling melodic sequences from the same music genre. We perform a comparative analysis of two probabilistic models; a Dirichlet Variable Length Markov Model (Dirichlet-VMM) and a Time Convolutional Restricted Boltzmann Machine (TC-RBM). We show that the TC-RBM learns descriptive music features, such as underlying chords and typical melody transitions and dynamics. We assess the models for future prediction and compare their performance to a VMM, which is the current state of the art in melody generation. We show that both models perform significantly better than the VMM, with the Dirichlet-VMM marginally outperforming the TC-RBM. Finally, we evaluate the short order statistics of the models, using the Kullback-Leibler divergence between test sequences and model samples, and show that our proposed methods match the statistics of the music genre significantly better than the VMM.

CERN European Organization for Nuclear Research - Zenodo, 2022

2017

Neural networks, and especially long short-term memory networks (LSTM), have become increasingly popular for sequence modelling, be it in text, speech, or music. In this paper, we investigate the predictive power of simple LSTM networks for polyphonic MIDI sequences, using an empirical approach. Such systems can then be used as a music language model which, combined with an acoustic model, can improve automatic music transcription (AMT) performance. As a first step, we experiment with synthetic MIDI data, and we compare the results obtained in various settings, throughout the training process. In particular, we compare the use of a fixed sample rate against a musically-relevant sample rate. We test this system both on synthetic and real MIDI data. Results are compared in terms of note prediction accuracy. We show that the higher the sample rate is, the better the prediction is, because self transitions are more frequent. We suggest that for AMT, a musically-relevant sample rate is crucial in order to model note transitions, beyond a simple smoothing effect.

2008

to achieve with traditional machine learning methods. This problem occurs when considering music data. In this paper, we introduce predictive models for melodies. We decompose melodic modeling into two subtasks. We first propose a rhythm model based on the distributions of distances between subsequences. Then, we define a generative model for melodies given chords and rhythms based on modeling sequences of Narmour features. The rhythm model consistently outperforms a standard Hidden Markov Model in terms of conditional prediction accuracy on two dierent music databases. Using a similar evaluation procedure, the proposed melodic model consistently outperforms an Input/Output Hidden Markov Model. Furthermore, these models are able to generate realistic melodies given appropriate musical contexts.

The wide-ranging impact of deep learning models implies significant application in music analysis, retrieval , and generation. Initial findings from musical application of a conditional restricted Boltzmann machine (CRBM) show promise towards informing creative computation. Taking advantage of the CRBM's ability to model temporal dependencies full reconstructions of pieces are achievable given a few starting seed notes. The generation of new material using figuration from the training corpus requires restrictions on the size and memory space of the CRBM, forcing associative rather than perfect recall. Musical analysis and information complexity measures show the musical encoding to be the primary determinant of the nature of the generated results.

Journal of New Music Research, 1995

This paper examines the prediction and generation of music using a multiple viewpoint system, a collection of independent views of the musical surface each of which models a specific type of musical phenomena. Both the general style and a particular piece are modeled using dual short-term and long-term theories, and the model is created using machine learning techniques on a corpus of musical examples.

2018

Melodic contour, the ‘shape’ of a melody, is a common way to visualize and remember a musical piece. The purpose of this paper is to explore the building blocks of a future ‘gesture-based’ melody retrieval system. We present a dataset containing 16 melodic phrases from four musical styles and with a large range of contour variability. This is accompanied by full-body motion capture data of 26 participants performing sound-tracing to the melodies. The dataset is analyzed using canonical correlation analysis (CCA), and its neural network variant (Deep CCA), to understand how melodic contours and sound tracings relate to each other. The analyses reveal non-linear relationships between sound and motion. The link between pitch and verticality does not appear strong enough for complex melodies. We also find that descending melodic contours have the least correlation with tracings.

The Thirty-Second AAAI Conference on Artificial Intelligence., 2018

We propose an end-to-end approach for modeling polyphonic music with a novel graphical representation, based on music theory, in a deep neural network. Despite the success of deep learning in various applications, it remains a challenge to incorporate existing domain knowledge in a network without affecting its training routines. In this paper we present a novel approach for predictive music modeling and music generation that incorporates domain knowledge in its representation. In this work, music is transformed into a 2D representation, inspired by tonnetz from music theory, which graphically encodes musical relationships between pitches. This representation is incorporated in a deep network structure consisting of multilayered convolutional neural networks (CNN, for learning an efficient abstract encoding of the representation) and recurrent neural networks with long short-term memory cells (LSTM, for capturing temporal dependencies in music sequences). We empirically evaluate the nature and the effectiveness of the network by using a dataset of classical music from various composers. We investigate the effect of parameters including the number of convolution feature maps, pooling strategies, and three configurations of the network: LSTM without CNN, LSTM with CNN (pre-trained vs. not pre-trained). Visualizations of the feature maps and filters in the CNN are explored, and a comparison is made between the proposed tonnetz-inspired representation and pianoroll, a commonly used representation of music in computational systems. Experimental results show that the tonnetz representation produces musical sequences that are more tonally stable and contain more repeated patterns than sequences generated by pianoroll-based models, a finding that is directly useful for tackling current challenges in music and AI such as smart music generation.

2019

We present a framework based on neural networks to extract music scores directly from polyphonic audio in an end-to-end fashion. Most previous Automatic Music Transcription (AMT) methods seek a piano-roll representation of the pitches, that can be further transformed into a score by incorporating tempo estimation, beat tracking, key estimation or rhythm quantization. Unlike these methods, our approach generates music notation directly from the input audio in a single stage. For this, we use a Convolutional Recurrent Neural Network (CRNN) with Connectionist Temporal Classification (CTC) loss function which does not require annotated alignments of audio frames with the score rhythmic information. We trained our model using as input Haydn, Mozart, and Beethoven string quartets and Bach chorales synthesized with different tempos and expressive performances. The output is a textual representation of four-voice music scores based on **kern format. Although the proposed approach is evaluat...