Automatic generation of sequences has been a highly explored field in the last years. In particular, natural language processing and automatic music composition have gained importance due to the recent advances in machine learning and Neural Networks with intrinsic memory mechanisms such as Recurrent Neural Networks. This paper evaluates different types of memory mechanisms (memory cells) and analyses their performance in the field of music composition. The proposed approach considers music theory concepts such as transposition, and uses data transformations (embeddings) to introduce semantic meaning and improve the quality of the generated melodies. A set of quantitative metrics is presented to evaluate the performance of the proposed architecture automatically, measuring the tonality of the musical compositions.
This paper introduces a novel recurrent model for music composition that is tailored to the structure of polyphonic music. We propose an efficient new conditional probabilistic factorization of musical scores, viewing a score as a collection of concurrent, coupled sequences: i.e. voices. To model the conditional distributions, we borrow ideas from both convolutional and recurrent neural models; we argue that these ideas are natural for capturing music's pitch invariances, temporal structure, and polyphony. We train models for single-voice and multi-voice composition on 2,300 scores from the Ke…
Acoustic environment characterization opens doors for sound reproduction innovations, smart EQing, speech enhancement, hearing aids, and forensics. Reverberation time, clarity, and direct-to-reverberant ratio are acoustic parameters that have been defined to describe reverberant environments. They are closely related to speech intelligibility and sound quality. As explained in the ISO3382 standard, they can be derived from a room measurement called the Room Impulse Response (RIR). However, measuring RIRs requires specific equipment and intrusive sound to be played. The recent audio combined wi…
We present a model for capturing musical features and creating novel sequences of music, called the Convolutional Variational Recurrent Neural Network. To generate sequential data, the model uses an encoder-decoder architecture with latent probabilistic connections to capture the hidden structure of music. Using the sequence-to-sequence model, our generative model can exploit samples from a prior distribution and generate a longer sequence of music. We compare the performance of our proposed model with other types of Neural Networks using the criteria of Information Rate that is implemented by…
Tampere University of Technology（坦佩雷理工大学）；University of Zilina（日利纳大学）
This paper studies the emotion recognition from musical tracks in the 2-dimensional valence-arousal (V-A) emotional space. We propose a method based on convolutional (CNN) and recurrent neural networks (RNN), having significantly fewer parameters compared with the state-of-the-art method for the same task. We utilize one CNN layer followed by two branches of RNNs trained separately for arousal and valence. The method was evaluated using the 'MediaEval2015 emotion in music' dataset. We achieved an RMSE of 0.202 for arousal and 0.268 for valence, which is the best result reported on this dataset…
Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences（中国科学院声学研究所噪声与振动研究重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；State Key Laboratory of Media Convergence and Communication, Communication University of China（中国传媒大学媒体融合与传播国家重点实验室）；School of Electronics and Communication Engineering, Guangzhou University（广州大学电子与通信工程学院）；National Environmental Protection Engineering and Technology Center for Road Traffic Noise Control（国家环境保护道路交通噪声控制工程技术中心）
With the development of deep neural networks, automatic music composition has made great progress. Although emotional music can evoke listeners' different emotions and it is important for artistic expression, only few researches have focused on generating emotional music. This paper presents EmotionBox -an music-element-driven emotional music generator that is capable of composing music given a specific emotion, where this model does not require a music dataset labeled with emotions. Instead, pitch histogram and note density are extracted as features that represent mode and tempo respectively …
A recurrent Neural Network (RNN) is trained to predict sound samples based on audio input augmented by control parameter information for pitch, volume, and instrument identification. During the generative phase following training, audio input is taken from the output of the previous time step, and the parameters are externally controlled allowing the network to be played as a musical instrument. Building on an architecture developed in previous work, we focus on the learning and synthesis of transients - the temporal response of the network during the short time (tens of milliseconds) followin…
Queen Mary University of London（伦敦玛丽女王大学）；New York University（纽约大学）
We introduce a convolutional recurrent neural network (CRNN) for music tagging. CRNNs take advantage of convolutional neural networks (CNNs) for local feature extraction and recurrent neural networks for temporal summarisation of the extracted features. We compare CRNN with three CNN structures that have been used for music tagging while controlling the number of parameters with respect to their performance and training time per sample. Overall, we found that CRNNs show a strong performance with respect to the number of parameter and training time, indicating the effectiveness of its hybrid st…
Deep learning has been demonstrated its effectiveness and efficiency in music genre classification. However, the existing achievements still have several shortcomings which impair the performance of this classification task. In this paper, we propose a hybrid architecture which consists of the paralleling CNN and Bi-RNN blocks. They focus on spatial features and temporal frame orders extraction respectively. Then the two outputs are fused into one powerful representation of musical signals and fed into softmax function for classification. The paralleling network guarantees the extracting featu…
Research Center for IT Innovation Academia Sinica Taipei, Taiwan
Convolutional neural networks with skip connections have shown good performance in music source separation. In this work, we propose a denoising Auto-encoder with Recurrent skip Connections (ARC). We use 1D convolution along the temporal axis of the time-frequency feature map in all layers of the fully-convolutional network. The use of 1D convolution makes it possible to apply recurrent layers to the intermediate outputs of the convolution layers. In addition, we also propose an enhancement network and a residual regression method to further improve the separation result. The recurrent skip co…
Max Planck Institute for Mathematics in the Sciences（马克斯·普朗克数学科学研究所）；Yandex（扬德克斯）
A new architecture of an artificial neural network that helps to generate longer melodic patterns is introduced alongside with methods for post-generation filtering. The proposed approach called variational autoencoder supported by history is based on a recurrent highway gated network combined with a variational autoencoder. Combination of this architecture with filtering heuristics allows generating pseudo-live acoustically pleasing and melodically diverse music.
Memorial University of Newfoundland（纽芬兰纪念大学）；University of Waterloo（滑铁卢大学）
In this paper we present a method for algorithmic melody generation using a generative adversarial network without recurrent components. Music generation has been successfully done using recurrent neural networks, where the model learns sequence information that can help create authentic sounding melodies. Here, we use DC-GAN architecture with dilated convolutions and towers to capture sequential information as spatial image information, and learn long-range dependencies in fixed-length melody forms such as Irish traditional reel.
Clova AI Research（Clova人工智能研究院）；NAVER Corp.（NAVER公司）；Hong Kong University of Science and Technology（香港科技大学）
Music highlights are valuable contents for music services. Most methods focused on low-level signal features. We propose a method for extracting highlights using high-level features from convolutional recurrent attention networks (CRAN). CRAN utilizes convolution and recurrent layers for sequential learning with an attention mechanism. The attention allows CRAN to capture significant snippets for distinguishing between genres, thus being used as a high-level feature. CRAN was evaluated on over 32,000 popular tracks in Korea for two months. Experimental results show our method outperforms three…
Previous attempts at music artist classification use frame level audio features which summarize frequency content within short intervals of time. Comparatively, more recent music information retrieval tasks take advantage of temporal structure in audio spectrograms using deep convolutional and recurrent models. This paper revisits artist classification with this new framework and empirically explores the impacts of incorporating temporal structure in the feature representation. To this end, an established classification architecture, a Convolutional Recurrent Neural Network (CRNN), is applied …
Algorithmic music composition is a way of composing musical pieces with minimal to no human intervention. While recurrent neural networks are traditionally applied to many sequence-to-sequence prediction tasks, including successful implementations of music composition, their standard supervised learning approach based on input-to-output mapping leads to a lack of note variety. These models can therefore be seen as potentially unsuitable for tasks such as music generation. Generative adversarial networks learn the generative distribution of data and lead to varied samples. This work implements …
This study investigates the use of non-linear unsupervised dimensionality reduction techniques to compress a music dataset into a low-dimensional representation which can be used in turn for the synthesis of new sounds. We systematically compare (shallow) autoencoders (AEs), deep autoencoders (DAEs), recurrent autoencoders (with Long Short-Term Memory cells -- LSTM-AEs) and variational autoencoders (VAEs) with principal component analysis (PCA) for representing the high-resolution short-term magnitude spectrum of a large and dense dataset of music notes into a lower-dimensional vector (and the…
This paper describes a neural drum transcription method that detects from music signals the onset times of drums at the $\textit{tatum}$ level, where tatum times are assumed to be estimated in advance. In conventional studies on drum transcription, deep neural networks (DNNs) have often been used to take a music spectrogram as input and estimate the onset times of drums at the $\textit{frame}$ level. The major problem with such frame-to-frame DNNs, however, is that the estimated onset times do not often conform with the typical tatum-level patterns appearing in symbolic drum scores because the…
Our goal is to be able to build a generative model from a deep neural network architecture to try to create music that has both harmony and melody and is passable as music composed by humans. Previous work in music generation has mainly been focused on creating a single melody. More recent work on polyphonic music modeling, centered around time series probability density estimation, has met some partial success. In particular, there has been a lot of work based off of Recurrent Neural Networks combined with Restricted Boltzmann Machines (RNN-RBM) and other similar recurrent energy based models…
As digital music production has become mainstream, the selection of appropriate virtual instruments plays a crucial role in determining the quality of music. To search the musical instrument samples or virtual instruments that make one's desired sound, music producers use their ears to listen and compare each instrument sample in their collection, which is time-consuming and inefficient. In this paper, we call this task as Musical Instrument Retrieval and propose a method for retrieving desired musical instruments using reference music mixture as a query. The proposed model consists of the Sin…
This paper is about creating digital musical instruments where a predictive neural network model is integrated into the interactive system. Rather than predicting symbolic music (e.g., MIDI notes), we suggest that predicting future control data from the user and precise temporal information can lead to new and interesting interactive possibilities. We propose that a mixture density recurrent neural network (MDRNN) is an appropriate model for this task. The predictions can be used to fill-in control data when the user stops performing, or as a kind of filter on the user's own input. We present …
T-Brain X；SK Telecom（SK电讯）；Graduate School of Culture Technology（文化技术研究生院）；KAIST（韩国科学技术院）
The goal of this paper to generate a visually appealing video that responds to music with a neural network so that each frame of the video reflects the musical characteristics of the corresponding audio clip. To achieve the goal, we propose a neural music visualizer directly mapping deep music embeddings to style embeddings of StyleGAN, named TräumerAI, which consists of a music auto-tagging model using short-chunk CNN and StyleGAN2 pre-trained on WikiArt dataset. Rather than establishing an objective metric between musical and visual semantics, we manually labeled the pairs in a subjective ma…
Advancements in the digital technologies have enabled researchers to develop a variety of Computational Music applications. Such applications are required to capture, process, and generate data related to music. Therefore, it is important to digitally represent music in a music theoretic and concise manner. Existing approaches for representing music are ineffective in terms of utilizing music theory. In this paper, we address the disjoint of music theory and computational music by developing an opensource representation tool based on music theory. Through the wide range of use cases, we run an…
A key aspect of machine learning models lies in their ability to learn efficient intermediate features. However, the input representation plays a crucial role in this process, and polyphonic musical scores remain a particularly complex type of information. In this paper, we introduce a novel representation of symbolic music data, which transforms a polyphonic score into a continuous signal. We evaluate the ability to learn meaningful features from this representation from a musical point of view. Hence, we introduce an evaluation method relying on principled generation of synthetic data. Final…
Emotion is a complicated notion present in music that is hard to capture even with fine-tuned feature engineering. In this paper, we investigate the utility of state-of-the-art pre-trained deep audio embedding methods to be used in the Music Emotion Recognition (MER) task. Deep audio embedding methods allow us to efficiently capture the high dimensional features into a compact representation. We implement several multi-class classifiers with deep audio embeddings to predict emotion semantics in music. We investigate the effectiveness of L3-Net and VGGish deep audio embedding methods for music …
University of California San Diego（加利福尼亚大学圣地亚哥分校）；Tencent Music Entertainment（腾讯音乐娱乐）
Personalized recommendation on new track releases has always been a challenging problem in the music industry. To combat this problem, we first explore user listening history and demographics to construct a user embedding representing the user's music preference. With the user embedding and audio data from user's liked and disliked tracks, an audio embedding can be obtained for each track using metric learning with Siamese networks. For a new track, we can decide the best group of users to recommend by computing the similarity between the track's audio embedding and different user embeddings, …
Singapore University of Technology and Design（新加坡科技设计大学）
The rise of deep learning technologies has quickly advanced many fields, including that of generative music systems. There exist a number of systems that allow for the generation of good sounding short snippets, yet, these generated snippets often lack an overarching, longer-term structure. In this work, we propose CM-HRNN: a conditional melody generation model based on a hierarchical recurrent neural network. This model allows us to generate melodies with long-term structures based on given chord accompaniments. We also propose a novel, concise event-based representation to encode musical lea…
Music Technology Group, Universitat Pompeu Fabra（庞培法布拉大学音乐技术组）；Dolby Laboratories（杜比实验室）；European Commission, Joint Research Centre（欧盟委员会联合研究中心）
Version identification systems aim to detect different renditions of the same underlying musical composition (loosely called cover songs). By learning to encode entire recordings into plain vector embeddings, recent systems have made significant progress in bridging the gap between accuracy and scalability, which has been a key challenge for nearly two decades. In this work, we propose to further narrow this gap by employing a set of data distillation techniques that reduce the embedding dimensionality of a pre-trained state-of-the-art model. We compare a wide range of techniques and propose n…
Isolating individual instruments in a musical mixture has a myriad of potential applications, and seems imminently achievable given the levels of performance reached by recent deep learning methods. While most musical source separation techniques learn an independent model for each instrument, we propose using a common embedding space for the time-frequency bins of all instruments in a mixture inspired by deep clustering and deep attractor networks. Additionally, an auxiliary network is used to generate parameters of a Gaussian mixture model (GMM) where the posterior distribution over GMM comp…
The Variational Autoencoder (VAE) has proven to be an effective model for producing semantically meaningful latent representations for natural data. However, it has thus far seen limited application to sequential data, and, as we demonstrate, existing recurrent VAE models have difficulty modeling sequences with long-term structure. To address this issue, we propose the use of a hierarchical decoder, which first outputs embeddings for subsequences of the input and then uses these embeddings to generate each subsequence independently. This structure encourages the model to utilize its latent cod…
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…
Waseda University（早稻田大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Honda Research Institute Japan（日本本田研究所）
Synthesizing human's movements such as dancing is a flourishing research field which has several applications in computer graphics. Recent studies have demonstrated the advantages of deep neural networks (DNNs) for achieving remarkable performance in motion and music tasks with little effort for feature pre-processing. However, applying DNNs for generating dance to a piece of music is nevertheless challenging, because of 1) DNNs need to generate large sequences while mapping the music input, 2) the DNN needs to constraint the motion beat to the music, and 3) DNNs require a considerable amount …
Nankai University（南开大学）；National University of Singapore（新加坡国立大学）；Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）；Tsinghua University（清华大学）
Definitive embeddings remain a fundamental challenge of computational musicology for symbolic music in deep learning today. Analogous to natural language, music can be modeled as a sequence of tokens. This motivates the majority of existing solutions to explore the utilization of word embedding models to build music embeddings. However, music differs from natural languages in two key aspects: (1) musical token is multi-faceted -- it comprises of pitch, rhythm and dynamics information; and (2) musical context is two-dimensional -- each musical token is dependent on both melodic and harmonic con…
Institute of Computational Perception, JKU Linz（林茨约翰·开普勒大学计算感知研究所）；Sony Computer Science Laboratories (CSL)（索尼计算机科学实验室）
Connectionist sequence models (e.g., RNNs) applied to musical sequences suffer from two known problems: First, they have strictly "absolute pitch perception". Therefore, they fail to generalize over musical concepts which are commonly perceived in terms of relative distances between pitches (e.g., melodies, scale types, modes, cadences, or chord types). Second, they fall short of capturing the concepts of repetition and musical form. In this paper we introduce the recurrent gated autoencoder (RGAE), a recurrent neural network which learns and operates on interval representations of musical seq…
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 implementation of one such application in the form of an assistance tool designed for live improvisational performances by laptop ensembles. The primary intention was to leverage off-the-shelf pre-trained NN models as a basis for assisting individual performers either as musical novices looking to engage with more experienced performers or as a tool to expand musi…
Google Research（谷歌研究院）；Seoul National University（首尔大学）
Music tagging and content-based retrieval systems have traditionally been constructed using pre-defined ontologies covering a rigid set of music attributes or text queries. This paper presents MuLan: a first attempt at a new generation of acoustic models that link music audio directly to unconstrained natural language music descriptions. MuLan takes the form of a two-tower, joint audio-text embedding model trained using 44 million music recordings (370K hours) and weakly-associated, free-form text annotations. Through its compatibility with a wide range of music genres and text styles (includi…
Recent directions in automatic speech recognition (ASR) research have shown that applying deep learning models from image recognition challenges in computer vision is beneficial. As automatic music transcription (AMT) is superficially similar to ASR, in the sense that methods often rely on transforming spectrograms to symbolic sequences of events (e.g. words or notes), deep learning should benefit AMT as well. In this work, we outline an online polyphonic pitch detection system that streams audio to MIDI by ConvLSTMs. Our system achieves state-of-the-art results on the 2007 MIREX multi-F0 deve…
Music that is generated by recurrent neural networks often lacks a sense of direction and coherence. We therefore propose a two-stage LSTM-based model for lead sheet generation, in which the harmonic and rhythmic templates of the song are produced first, after which, in a second stage, a sequence of melody notes is generated conditioned on these templates. A subjective listening test shows that our approach outperforms the baselines and increases perceived musical coherence.
Central Conservatory of Music（中央音乐学院）；Tsinghua University（清华大学）
In natural language processing (NLP), the semantic similarity task requires large-scale, high-quality human-annotated labels for fine-tuning or evaluation. By contrast, in cases of music similarity, such labels are expensive to collect and largely dependent on the annotator's artistic preferences. Recent research has demonstrated that embedding calibration technique can greatly increase semantic similarity performance of the pre-trained language model without fine-tuning. However, it is yet unknown which calibration method is the best and how much performance improvement can be achieved. To ad…
Tampere University（坦佩雷大学）；Fraunhofer-IDMT（弗劳恩霍夫数字媒体技术研究所）
Recent approaches for music source separation are almost exclusively based on deep neural networks, mostly employing recurrent neural networks (RNNs). Although RNNs are in many cases superior than other types of deep neural networks for sequence processing, they are known to have specific difficulties in training and parallelization, especially for the typically long sequences encountered in music source separation. In this paper we present a use-case of replacing RNNs with depth-wise separable (DWS) convolutions, which are a lightweight and faster variant of the typical convolutions. We focus…
Music generation has generally been focused on either creating scores or interpreting them. We discuss differences between these two problems and propose that, in fact, it may be valuable to work in the space of direct $\it performance$ generation: jointly predicting the notes $\it and$ $\it also$ their expressive timing and dynamics. We consider the significance and qualities of the data set needed for this. Having identified both a problem domain and characteristics of an appropriate data set, we show an LSTM-based recurrent network model that subjectively performs quite well on this task. C…
