Music segmentation refers to the dual problem of identifying boundaries between, and labeling, distinct music segments, e.g., the chorus, verse, bridge etc. in popular music. The performance of a range of music segmentation algorithms has been shown to be dependent on the audio features chosen to represent the audio. Some approaches have proposed learning feature transformations from music segment annotation data, although, such data is time consuming or expensive to create and as such these approaches are likely limited by the size of their datasets. While annotated music segmentation data is a scarce resource, the amount of available music audio is much greater. In the neighboring field of semantic audio unsupervised deep learning has shown promise in improving the performance of solutions to the query-by-example and sound classification tasks. In this work, unsupervised training of deep feature embeddings using convolutional neural networks (CNNs) is explored for music segmentation. The proposed techniques exploit only the time proximity of audio features that is implicit in any audio timeline. Employing these embeddings in a classic music segmentation algorithm is shown not only to significantly improve the performance of this algorithm, but obtain state of the art performance in unsupervised music segmentation.
The Swiss AI Lab, IDSIA, USI & SUPSI（瑞士人工智能实验室，IDSIA，卢加诺大学与瑞士南部应用科学与艺术大学）；Institute of Neuroinformatics, ETH Zurich（苏黎世联邦理工学院神经信息学研究所）；AI Initiative, KAUST（阿卜杜拉国王科技大学人工智能计划）
We showcase an unsupervised method that repurposes deep models trained for music generation and music tagging for audio source separation, without any retraining. An audio generation model is conditioned on an input mixture, producing a latent encoding of the audio used to generate audio. This generated audio is fed to a pretrained music tagger that creates source labels. The cross-entropy loss between the tag distribution for the generated audio and a predefined distribution for an isolated source is used to guide gradient ascent in the (unchanging) latent space of the generative model. This …
Symbolic music segmentation is the process of dividing symbolic melodies into smaller meaningful groups, such as melodic phrases. We proposed an unsupervised method for segmenting symbolic music. The proposed model is based on an ensemble of temporal prediction error models. During training, each model predicts the next token to identify musical phrase changes. While at test time, we perform a peak detection algorithm to select segment candidates. Finally, we aggregate the predictions of each of the models participating in the ensemble to predict the final segmentation. Results suggest the pro…
In this work, we provide a broad comparative analysis of strategies for pre-training audio understanding models for several tasks in the music domain, including labelling of genre, era, origin, mood, instrumentation, key, pitch, vocal characteristics, tempo and sonority. Specifically, we explore how the domain of pre-training datasets (music or generic audio) and the pre-training methodology (supervised or unsupervised) affects the adequacy of the resulting audio embeddings for downstream tasks. We show that models trained via supervised learning on large-scale expert-annotated music datasets …
National Institute of Informatics（国立信息学研究所）；SOKENDAI（综合研究大学院大学）
Sheet music, audio, and lyrics are three main modalities during writing a song. In this paper, we propose an unsupervised generative adversarial alignment representation (UGAAR) model to learn deep discriminative representations shared across three major musical modalities: sheet music, lyrics, and audio, where a deep neural network based architecture on three branches is jointly trained. In particular, the proposed model can transfer the strong relationship between audio and sheet music to audio-lyrics and sheet-lyrics pairs by learning the correlation in the latent shared subspace. We apply …
Structure perception is a fundamental aspect of music cognition in humans. Historically, the hierarchical organization of music into structures served as a narrative device for conveying meaning, creating expectancy, and evoking emotions in the listener. Thereby, musical structures play an essential role in music composition, as they shape the musical discourse through which the composer organises his ideas. In this paper, we present a novel music segmentation method, pitchclass2vec, based on symbolic chord annotations, which are embedded into continuous vector representations using both natur…
Symbolic Music Generation relies on the contextual representation capabilities of the generative model, where the most prevalent approach is the Transformer-based model. The learning of musical context is also related to the structural elements in music, i.e. intro, verse, and chorus, which are currently overlooked by the research community. In this paper, we propose a hierarchical Transformer model to learn multi-scale contexts in music. In the encoding phase, we first designed a Fragment Scope Localization layer to syncopate the music into chords and sections. Then, we use a multi-scale atte…
We propose a novel system that takes as an input body movements of a musician playing a musical instrument and generates music in an unsupervised setting. Learning to generate multi-instrumental music from videos without labeling the instruments is a challenging problem. To achieve the transformation, we built a pipeline named 'Multi-instrumentalistNet' (MI Net). At its base, the pipeline learns a discrete latent representation of various instruments music from log-spectrogram using a Vector Quantized Variational Autoencoder (VQ-VAE) with multi-band residual blocks. The pipeline is then traine…
Disentangled sequential autoencoders (DSAEs) represent a class of probabilistic graphical models that describes an observed sequence with dynamic latent variables and a static latent variable. The former encode information at a frame rate identical to the observation, while the latter globally governs the entire sequence. This introduces an inductive bias and facilitates unsupervised disentanglement of the underlying local and global factors. In this paper, we show that the vanilla DSAE suffers from being sensitive to the choice of model architecture and capacity of the dynamic latent variable…
Télécom Paris, Institut Polytechnique de Paris（巴黎理工学院巴黎电信学院）；Sonos Inc.（搜诺思公司）
Supervised deep learning approaches to underdetermined audio source separation achieve state-of-the-art performance but require a dataset of mixtures along with their corresponding isolated source signals. Such datasets can be extremely costly to obtain for musical mixtures. This raises a need for unsupervised methods. We propose a novel unsupervised model-based deep learning approach to musical source separation. Each source is modelled with a differentiable parametric source-filter model. A neural network is trained to reconstruct the observed mixture as a sum of the sources by estimating th…
Recent work has proposed the use of tensor decomposition to model repetitions and to separate tracks in loop-based electronic music. The present work investigates further on the ability of Nonnegative Tucker Decompositon (NTD) to uncover musical patterns and structure in pop songs in their audio form. Exploiting the fact that NTD tends to express the content of bars as linear combinations of a few patterns, we illustrate the ability of the decomposition to capture and single out repeated motifs in the corresponding compressed space, which can be interpreted from a musical viewpoint. The result…
Removing reverb from reverberant music is a necessary technique to clean up audio for downstream music manipulations. Reverberation of music contains two categories, natural reverb, and artificial reverb. Artificial reverb has a wider diversity than natural reverb due to its various parameter setups and reverberation types. However, recent supervised dereverberation methods may fail because they rely on sufficiently diverse and numerous pairs of reverberant observations and retrieved data for training in order to be generalizable to unseen observations during inference. To resolve these proble…
University of Plymouth（普利茅斯大学）；University of Glasgow（格拉斯哥大学）；Anglia Ruskin University（安格利亚鲁斯金大学）；Brighton and Sussex Medical School（布莱顿与苏塞克斯医学院）
Segmenting audio into homogeneous sections such as music and speech helps us understand the content of audio. It is useful as a pre-processing step to index, store, and modify audio recordings, radio broadcasts and TV programmes. Deep learning models for segmentation are generally trained on copyrighted material, which cannot be shared. Annotating these datasets is time-consuming and expensive and therefore, it significantly slows down research progress. In this study, we present a novel procedure that artificially synthesises data that resembles radio signals. We replicate the workflow of a r…
Music signals are difficult to interpret from their low-level features, perhaps even more than images: e.g. highlighting part of a spectrogram or an image is often insufficient to convey high-level ideas that are genuinely relevant to humans. In computer vision, concept learning was therein proposed to adjust explanations to the right abstraction level (e.g. detect clinical concepts from radiographs). These methods have yet to be used for MIR. In this paper, we adapt concept learning to the realm of music, with its particularities. For instance, music concepts are typically non-independent and…
Discovering "Words" in Music: Unsupervised Learning of Compositional Sparse Code for Symbolic Music
Central Conservatory of Music（中央音乐学院）；Department of Industrial Engineering, Ajou University（Ajou大学工业工程系）；Alibaba Group（阿里巴巴集团）；Bigai；Peking University（北京大学）
Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）
Speech, Music and Noise classification/segmentation is an important preprocessing step for audio processing/indexing. To this end, we propose a novel 1D Convolutional Neural Network (CNN) - SwishNet. It is a fast and lightweight architecture that operates on MFCC features which is suitable to be added to the front-end of an audio processing pipeline. We showed that the performance of our network can be improved by distilling knowledge from a 2D CNN, pretrained on ImageNet. We investigated the performance of our network on the MUSAN corpus - an openly available comprehensive collection of noise…
National Tsing-Hua University（国立清华大学）；Academia Sinica（中央研究院）
Style transfer of polyphonic music recordings is a challenging task when considering the modeling of diverse, imaginative, and reasonable music pieces in the style different from their original one. To achieve this, learning stable multi-modal representations for both domain-variant (i.e., style) and domain-invariant (i.e., content) information of music in an unsupervised manner is critical. In this paper, we propose an unsupervised music style transfer method without the need for parallel data. Besides, to characterize the multi-modal distribution of music pieces, we employ the Multi-modal Un…
University of Sheffield（谢菲尔德大学）；Aalborg Universitet København（奥尔堡大学哥本哈根校区）；Universitat Pompeu Fabra（庞培法布拉大学）；Berlin Institute of Technology（柏林工业大学）
A system is presented that segments, clusters and predicts musical audio in an unsupervised manner, adjusting the number of (timbre) clusters instantaneously to the audio input. A sequence learning algorithm adapts its structure to a dynamically changing clustering tree. The flow of the system is as follows: 1) segmentation by onset detection, 2) timbre representation of each segment by Mel frequency cepstrum coefficients, 3) discretization by incremental clustering, yielding a tree of different sound classes (e.g. instruments) that can grow or shrink on the fly driven by the instantaneous sou…
Structural segmentation of music refers to the task of finding a symbolic representation of the organisation of a song, reducing the musical flow to a partition of non-overlapping segments. Under this definition, the musical structure may not be unique, and may even be ambiguous. One way to resolve that ambiguity is to see this task as a compression process, and to consider the musical structure as the optimization of a given compression criteria. In that viewpoint, C. Guichaoua developed a compression-driven model for retrieving the musical structure, based on the "System and Contrast" model,…
Aragón Institute for Engineering Research (I3A), University of Zaragoza（萨拉戈萨大学阿拉贡工程研究所（I3A））
Area under the ROC curve (AUC) optimisation techniques developed for neural networks have recently demonstrated their capabilities in different audio and speech related tasks. However, due to its intrinsic nature, AUC optimisation has focused only on binary tasks so far. In this paper, we introduce an extension to the AUC optimisation framework so that it can be easily applied to an arbitrary number of classes, aiming to overcome the issues derived from training data limitations in deep learning solutions. Building upon the multiclass definitions of the AUC metric found in the literature, we d…
Automated melodic phrase detection and segmentation is a classical task in content-based music information retrieval and also the key towards automated music structure analysis. However, traditional methods still cannot satisfy practical requirements. In this paper, we explore and adapt various neural network architectures to see if they can be generalized to work with the symbolic representation of music and produce satisfactory melodic phrase segmentation. The main issue of applying deep-learning methods to phrase detection is the sparse labeling problem of training sets. We proposed two tai…
NAVER Corp.（NAVER公司）；Graduate School of Culture Technology, KAIST（韩国科学技术院文化技术研究生院）
In music domain, feature learning has been conducted mainly in two ways: unsupervised learning based on sparse representations or supervised learning by semantic labels such as music genre. However, finding discriminative features in an unsupervised way is challenging and supervised feature learning using semantic labels may involve noisy or expensive annotation. In this paper, we present a supervised feature learning approach using artist labels annotated in every single track as objective meta data. We propose two deep convolutional neural networks (DCNN) to learn the deep artist features. O…
Many methods for automatic music transcription involves a multi-pitch estimation method that estimates an activity score for each pitch. A second processing step, called note segmentation, has to be performed for each pitch in order to identify the time intervals when the notes are played. In this study, a pitch-wise two-state on/off firstorder Hidden Markov Model (HMM) is developed for note segmentation. A complete parametrization of the HMM sigmoid function is proposed, based on its original regression formulation, including a parameter alpha of slope smoothing and beta? of thresholding cont…
National Institute of Science and Technology for Complex Systems（国家复杂系统科学技术研究所）
Online music databases have increased signicantly as a consequence of the rapid growth of the Internet and digital audio, requiring the development of faster and more efficient tools for music content analysis. Musical genres are widely used to organize music collections. In this paper, the problem of automatic music genre classification is addressed by exploring rhythm-based features obtained from a respective complex network representation. A Markov model is build in order to analyse the temporal sequence of rhythmic notation events. Feature analysis is performed by using two multivariate st…
Fraunhofer-IDMT（弗劳恩霍夫数字媒体技术研究所）；Tampere University（坦佩雷大学）；Technical University of Ilmenau（伊尔梅瑙工业大学）
In this work, we present a method for learning interpretable music signal representations directly from waveform signals. Our method can be trained using unsupervised objectives and relies on the denoising auto-encoder model that uses a simple sinusoidal model as decoding functions to reconstruct the singing voice. To demonstrate the benefits of our method, we employ the obtained representations to the task of informed singing voice separation via binary masking, and measure the obtained separation quality by means of scale-invariant signal to distortion ratio. Our findings suggest that our me…
Indian Institute of Technology, Kharagpur（印度理工学院克勒格布尔分校）；Indian Statistical Institute, Kolkata（印度统计研究所加尔各答分所）
This work aims to examine one of the cornerstone problems of Musical Instrument Retrieval (MIR), in particular, instrument classification. IRMAS (Instrument recognition in Musical Audio Signals) data set is chosen for this purpose. The data includes musical clips recorded from various sources in the last century, thus having a wide variety of audio quality. We have presented a very concise summary of past work in this domain. Having implemented various supervised learning algorithms for this classification task, SVM classifier has outperformed the other state-of-the-art models with an accuracy…
ENSTA Bretagne（布列塔尼国立高等先进技术学校）；Université Européenne de Bretagne（布列塔尼欧洲大学）；Université Paris Descartes（巴黎笛卡尔大学）
Hidden Markov Models (HMMs) are a ubiquitous tool to model time series data, and have been widely used in two main tasks of Automatic Music Transcription (AMT): note segmentation, i.e. identifying the played notes after a multi-pitch estimation, and sequential post-processing, i.e. correcting note segmentation using training data. In this paper, we employ the multi-pitch estimation method called Probabilistic Latent Component Analysis (PLCA), and develop AMT systems by integrating different HMM-based modules in this framework. For note segmentation, we use two different twostate on/o? HMMs, in…
Korea Advanced Institute of Science and Technology（韩国科学技术院）；Stanford University（斯坦福大学）；Seoul National University（首尔大学）
Feature learning and deep learning have drawn great attention in recent years as a way of transforming input data into more effective representations using learning algorithms. Such interest has grown in the area of music information retrieval (MIR) as well, particularly in music audio classification tasks such as auto-tagging. In this paper, we present a two-stage learning model to effectively predict multiple labels from music audio. The first stage learns to project local spectral patterns of an audio track onto a high-dimensional sparse space in an unsupervised manner and summarizes the au…
Johannes Kepler University Linz（林茨约翰·开普勒大学）；Linz Institute of Technology（林茨理工学院）
Current approaches for explaining deep learning systems applied to musical data provide results in a low-level feature space, e.g., by highlighting potentially relevant time-frequency bins in a spectrogram or time-pitch bins in a piano roll. This can be difficult to understand, particularly for musicologists without technical knowledge. To address this issue, we focus on more human-friendly explanations based on high-level musical concepts. Our research targets trained systems (post-hoc explanations) and explores two approaches: a supervised one, where the user can define a musical concept and…
