In this work we describe and evaluate methods to learn musical embeddings. Each embedding is a vector that represents four contiguous beats of music and is derived from a symbolic representation. We consider autoencoding-based methods including denoising autoencoders, and context reconstruction, and evaluate the resulting embeddings on a forward prediction and a classification task.
Generative models in vision have seen rapid progress due to algorithmic improvements and the availability of high-quality image datasets. In this paper, we offer contributions in both these areas to enable similar progress in audio modeling. First, we detail a powerful new WaveNet-style autoencoder model that conditions an autoregressive decoder on temporal codes learned from the raw audio waveform. Second, we introduce NSynth, a large-scale and high-quality dataset of musical notes that is an order of magnitude larger than comparable public datasets. Using NSynth, we demonstrate improved qual…
Music is usually highly structured and it is still an open question how to design models which can successfully learn to recognize and represent musical structure. A fundamental problem is that structurally related patterns can have very distinct appearances, because the structural relationships are often based on transformations of musical material, like chromatic or diatonic transposition, inversion, retrograde, or rhythm change. In this preliminary work, we study the potential of two unsupervised learning techniques - Restricted Boltzmann Machines (RBMs) and Gated Autoencoders (GAEs) - to c…
In the stereo-to-multichannel upmixing problem for music, one of the main tasks is to set the directionality of the instrument sources in the multichannel rendering results. In this paper, we propose a modified variational autoencoder model that learns a latent space to describe the spatial images in multichannel music. We seek to disentangle the spatial images and music content, so the learned latent variables are invariant to the music. At test time, we use the latent variables to control the panning of sources. We propose two upmixing use cases: transferring the spatial images from one song…
We consider the problem of learning high-level controls over the global structure of generated sequences, particularly in the context of symbolic music generation with complex language models. In this work, we present the Transformer autoencoder, 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 representation with other temporally distributed embeddings, enabling improved control over the separate aspects of performance style and melody. Empirically, we demonstrate the eff…
Singapore University of Technology and Design（新加坡科技设计大学）；Institute of High Performance Computing, A*STAR（新加坡科技研究局高性能计算研究所）；Yong Siew Toh Conservatory of Music, National University of Singapore（新加坡大学杨秀桃音乐学院）
In this paper, we learn disentangled representations of timbre and pitch for musical instrument sounds. We adapt a framework based on variational autoencoders with Gaussian mixture latent distributions. Specifically, we use two separate encoders to learn distinct latent spaces for timbre and pitch, which form Gaussian mixture components representing instrument identity and pitch, respectively. For reconstruction, latent variables of timbre and pitch are sampled from corresponding mixture components, and are concatenated as the input to a decoder. We show the model efficacy by latent space visu…
The Cooper Union for the Advancement of Science and Art（库珀高等科学艺术联盟学院）
A method for musical audio synthesis using autoencoding neural networks is proposed. The autoencoder is trained to compress and reconstruct magnitude short-time Fourier transform frames. The autoencoder produces a spectrogram by activating its smallest hidden layer, and a phase response is calculated using real-time phase gradient heap integration. Taking an inverse short-time Fourier transform produces the audio signal. Our algorithm is light-weight when compared to current state-of-the-art audio-producing machine learning algorithms. We outline our design process, produce metrics, and detail…
Graduate School of Informatics（信息学研究生院）；Kyoto University（京都大学）
The original MV2H metric was designed to evaluate systems which transcribe from an input audio (or MIDI) piece to a complete musical score. However, it requires both the transcribed score and the ground truth score to be time-aligned with the input. Some recent work has begun to transcribe directly from an audio signal into a musical score, skipping the alignment step. This paper introduces an automatic alignment method based on dynamic time warp which allows for MV2H to be used to evaluate such non-aligned transcriptions. This has the additional benefit of allowing non-aligned musical scores-…
University of Southern California（南加州大学）；National Institute of Informatics（国立信息学研究所）
Constructing an embedding space for musical instrument sounds that can meaningfully represent new and unseen instruments is important for downstream music generation tasks such as multi-instrument synthesis and timbre transfer. The framework of Automatic Speaker Verification (ASV) provides us with architectures and evaluation methodologies for verifying the identities of unseen speakers, and these can be repurposed for the task of learning and evaluating a musical instrument sound embedding space that can support unseen instruments. Borrowing from state-of-the-art ASV techniques, we construct …
MSVAE: Rethinking Musical Semantics in Continuous Latent Spaces
Geely Automobile Research Institute (Ningbo) Company Ltd（吉利汽车研究院（宁波）有限公司）；Faculty of Electronic and Information Engineering, Xi’an Jiaotong University（西安交通大学电子与信息工程学院）；WeNet Open Source Community（WeNet开源社区）
Imperial College London（帝国理工学院）；University of Augsburg（奥格斯堡大学）
Despite advances in deep algorithmic music generation, evaluation of generated samples often relies on human evaluation, which is subjective and costly. We focus on designing a homogeneous, objective framework for evaluating samples of algorithmically generated music. Any engineered measures to evaluate generated music typically attempt to define the samples' musicality, but do not capture qualities of music such as theme or mood. We do not seek to assess the musical merit of generated music, but instead explore whether generated samples contain meaningful information pertaining to emotion or …
In this paper we explore techniques for generating new music using a Variational Autoencoder (VAE) neural network that was trained on a corpus of specific style. Instead of randomly sampling the latent states of the network to produce free improvisation, we generate new music by querying the network with musical input in a style different from the training corpus. This allows us to produce new musical output with longer-term structure that blends aspects of the query to the style of the network. In order to control the level of this blending we add a noisy channel between the VAE encoder and d…
RWTH Aachen University（亚琛工业大学）；University of Florence（佛罗伦萨大学）
We present a feature engineering pipeline for the construction of musical signal characteristics, to be used for the design of a supervised model for musical genre identification. The key idea is to extend the traditional two-step process of extraction and classification with additive stand-alone phases which are no longer organized in a waterfall scheme. The whole system is realized by traversing backtrack arrows and cycles between various stages. In order to give a compact and effective representation of the features, the standard early temporal integration is combined with other selection a…
Evaluating Latent Space Structure in Timbre VAEs: A Comparative Study of Unsupervised, Descriptor-Conditioned, and Perceptual Feature-Conditioned Models
Department of Computer Science \& Technology, University of Cambridge\ , United Kingdom
Speech embeddings are fixed-size acoustic representations of variable-length speech sequences. They are increasingly used for a variety of tasks ranging from information retrieval to unsupervised term discovery and speech segmentation. However, there is currently no clear methodology to compare or optimise the quality of these embeddings in a task-neutral way. Here, we systematically compare two popular metrics, ABX discrimination and Mean Average Precision (MAP), on 5 languages across 17 embedding methods, ranging from supervised to fully unsupervised, and using different loss functions (auto…
Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）；Universidade Federal do Estado do Rio de Janeiro（里约热内卢州联邦大学）；Pontifícia Universidade Católica do Rio de Janeiro（里约热内卢天主教大学）；Sony Computer Science Laboratories（索尼计算机科学实验室）；Spotify Creator Technology Research Lab（Spotify创作者技术研究实验室）
This paper is a survey and an analysis of different ways of using deep learning (deep artificial neural networks) to generate musical content. We propose a methodology based on five dimensions for our analysis: Objective - What musical content is to be generated? Examples are: melody, polyphony, accompaniment or counterpoint. - For what destination and for what use? To be performed by a human(s) (in the case of a musical score), or by a machine (in the case of an audio file). Representation - What are the concepts to be manipulated? Examples are: waveform, spectrogram, note, chord, meter and b…
