Generating music is an interesting and challenging problem in the field of machine learning. Mimicking human creativity has been popular in recent years, especially in the field of computer vision and image processing. With the advent of GANs, it is possible to generate new similar images, based on trained data. But this cannot be done for music similarly, as music has an extra temporal dimension. So it is necessary to understand how music is represented in digital form. When building models that perform this generative task, the learning and generation part is done in some high-level representation such as MIDI (Musical Instrument Digital Interface) or scores. This paper proposes a bi-directional LSTM (Long short-term memory) model with attention mechanism capable of generating similar type of music based on MIDI data. The music generated by the model follows the theme/style of the music the model is trained on. Also, due to the nature of MIDI, the tempo, instrument, and other parameters can be defined, and changed, post generation.
We will introduce BumbleBee, a transformer model that will generate MIDI music data . We will tackle the issue of transformers applied to long sequences by implementing a longformer generative model that uses dilating sliding windows to compute the attention layers. We will compare our results to that of the music transformer and Long-Short term memory (LSTM) to benchmark our results. This analysis will be performed using piano MIDI files, in particular , the JSB Chorales dataset that has already been used for other research works (Huang et al., 2018)
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…
Music classification between music made by AI or human composers can be done by deep learning networks. We first transformed music samples in midi format to natural language sequences, then classified these samples by mLSTM (multiplicative Long Short Term Memory) + logistic regression. The accuracy of the result evaluated by 10-fold cross validation can reach 90%. Our work indicates that music generated by AI and human composers do have different characteristics, which can be learned by deep learning networks.
Duke Kunshan University（昆山杜克大学）；Wuhan University（武汉大学）；Tiangong University（天津工业大学）；Tencent Inc.（腾讯公司）
Convolutional Neural Network (CNN) or Long short-term memory (LSTM) based models with the input of spectrogram or waveforms are commonly used for deep learning based audio source separation. In this paper, we propose a Sliced Attention-based neural network (Sams-Net) in the spectrogram domain for the music source separation task. It enables spectral feature interactions with multi-head attention mechanism, achieves easier parallel computing and has a larger receptive field compared with LSTMs and CNNs respectively. Experimental results on the MUSDB18 dataset show that the proposed method, with…
University of Science and Technology of China（中国科学技术大学）
Most existing neural network models for music generation explore how to generate music bars, then directly splice the music bars into a song. However, these methods do not explore the relationship between the bars, and the connected song as a whole has no musical form structure and sense of musical direction. To address this issue, we propose a Multi-model Multi-task Hierarchical Conditional VAE-GAN (Variational Autoencoder-Generative adversarial networks) networks, named MIDI-Sandwich, which combines musical knowledge, such as musical form, tonic, and melodic motion. The MIDI-Sandwich has two…
MIDI-sheet music alignment is the task of finding correspondences between a MIDI representation of a piece and its corresponding sheet music images. Rather than using optical music recognition to bridge the gap between sheet music and MIDI, we explore an alternative approach: projecting the MIDI data into pixel space and performing alignment in the image domain. Our method converts the MIDI data into a crude representation of the score that only contains rectangular floating notehead blobs, a process we call bootleg score synthesis. Furthermore, we project sheet music images into the same boot…
University of Sussex（萨塞克斯大学）；Singapore University of Technology and Design（新加坡科技设计大学）
We present a Python library, called Midi Miner, that can calculate tonal tension and classify different tracks. MIDI (Music Instrument Digital Interface) is a hardware and software standard for communicating musical events between digital music devices. It is often used for tasks such as music representation, communication between devices, and even music generation [5]. Tension is an essential element of the music listening experience, which can come from a number of musical features including timbre, loudness and harmony [3]. Midi Miner provides a Python implementation for the tonal tension m…
MIDI-LLaMA: An Instruction-Following Multimodal LLM for Symbolic Music Understanding
SensiLab, Monash University, Australia（Monash大学）；University of Sussex, Brighton, United Kingdom（Sussex大学）；School of Computing and Information Systems, The University of Melbourne, Australia（墨尔本大学计算机与信息系统学院）
We introduce MIDI-VAE, a neural network model based on Variational Autoencoders that is capable of handling polyphonic music with multiple instrument tracks, as well as modeling the dynamics of music by incorporating note durations and velocities. We show that MIDI-VAE can perform style transfer on symbolic music by automatically changing pitches, dynamics and instruments of a music piece from, e.g., a Classical to a Jazz style. We evaluate the efficacy of the style transfer by training separate style validation classifiers. Our model can also interpolate between short pieces of music, produce…
Snap Inc.（Snap公司）；University of California, Berkeley（加州大学伯克利分校）；University of California, Los Angeles（加州大学洛杉矶分校）
In this paper, we propose a recurrent neural network (RNN)-based MIDI music composition machine that is able to learn musical knowledge from existing Beatles' songs and generate music in the style of the Beatles with little human intervention. In the learning stage, a sequence of stylistically uniform, multiple-channel music samples was modeled by a RNN. In the composition stage, a short clip of randomly-generated music was used as a seed for the RNN to start music score prediction. To form structured music, segments of generated music from different seeds were concatenated together. To improv…
Creating MIDI music can be a practical challenge. In the past, working with it was difficult and frustrating to all but the most accomplished and determined. Now, however, we are offering a powerful Visual Basic program called MIDI-LAB, that is easy to learn, and instantly rewarding to even the newest users. MIDI-LAB has been developed to give users the ability to quickly create music with a limitless variety of tunes, tempos, speeds, volumes, instruments, rhythms and major scales. This program has a simple, intuitive, and user-friendly interface, which provides a straightforward way to enter …
This paper investigates a cross-modal retrieval problem in which a user would like to retrieve a passage of music from a MIDI file by taking a cell phone picture of a physical page of sheet music. While audio-sheet music retrieval has been explored by a number of works, this scenario is novel in that the query is a cell phone picture rather than a digital scan. To solve this problem, we introduce a mid-level feature representation called a bootleg score which explicitly encodes the rules of Western musical notation. We convert both the MIDI and the sheet music into bootleg scores using determi…
MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；Massachusetts Institute of Technology（麻省理工学院）
In this paper, we introduce Foley Music, a system that can synthesize plausible music for a silent video clip about people playing musical instruments. We first identify two key intermediate representations for a successful video to music generator: body keypoints from videos and MIDI events from audio recordings. We then formulate music generation from videos as a motion-to-MIDI translation problem. We present a Graph$-$Transformer framework that can accurately predict MIDI event sequences in accordance with the body movements. The MIDI event can then be converted to realistic music using an …
University of Science and Technology of China（中国科学技术大学）
Currently, almost all the multi-track music generation models use the Convolutional Neural Network (CNN) to build the generative model, while the Recurrent Neural Network (RNN) based models can not be applied in this task. In view of the above problem, this paper proposes a RNN-based Hierarchical Multi-modal Fusion Generation Variational Autoencoder (VAE) network, MIDI-Sandwich2, for multi-track symbolic music generation. Inspired by VQ-VAE2, MIDI-Sandwich2 expands the dimension of the original hierarchical model by using multiple independent Binary Variational Autoencoder (BVAE) models withou…
The Accordiatron is a new MIDI controller for real-time performance based on the paradigm of a conventional squeeze box or concertina. It translates the gestures of a performer to the standard communication protocol of MIDI, allowing for flexible mappings of performance data to sonic parameters. When used in conjunction with a realtime signal processing environment, the Accordiatron becomes an expressive, versatile musical instrument. A combination of sensory outputs providing both discrete and continuous data gives the subtle expressiveness and control necessary for interactive music.
This article investigates a cross-modal retrieval problem in which a user would like to retrieve a passage of music from a MIDI file by taking a cell phone picture of several lines of sheet music. This problem is challenging for two reasons: it has a significant runtime constraint since it is a user-facing application, and there is very little relevant training data containing cell phone images of sheet music. To solve this problem, we introduce a novel feature representation called a bootleg score which encodes the position of noteheads relative to staff lines in sheet music. The MIDI represe…
EPFL（洛桑联邦理工学院）；University of Edinburgh（爱丁堡大学）；Kyoto University（京都大学）
In this paper, we introduce the MIDI Degradation Toolkit (MDTK), containing functions which take as input a musical excerpt (a set of notes with pitch, onset time, and duration), and return a "degraded" version of that excerpt with some error (or errors) introduced. Using the toolkit, we create the Altered and Corrupted MIDI Excerpts dataset version 1.0 (ACME v1.0), and propose four tasks of increasing difficulty to detect, classify, locate, and correct the degradations. We hypothesize that models trained for these tasks can be useful in (for example) improving automatic music transcription pe…
Symbolic music datasets are important for music information retrieval and musical analysis. However, there is a lack of large-scale symbolic datasets for classical piano music. In this article, we create a GiantMIDI-Piano (GP) dataset containing 38,700,838 transcribed notes and 10,855 unique solo piano works composed by 2,786 composers. We extract the names of music works and the names of composers from the International Music Score Library Project (IMSLP). We search and download their corresponding audio recordings from the internet. We further create a curated subset containing 7,236 works c…
Music classification is a task to classify a music piece into labels such as genres or composers. We propose large-scale MIDI based composer classification systems using GiantMIDI-Piano, a transcription-based dataset. We propose to use piano rolls, onset rolls, and velocity rolls as input representations and use deep neural networks as classifiers. To our knowledge, we are the first to investigate the composer classification problem with up to 100 composers. By using convolutional recurrent neural networks as models, our MIDI based composer classification system achieves a 10-composer and a 10…
Despite recent achievements of deep learning automatic music generation algorithms, few approaches have been proposed to evaluate whether a single-track music excerpt is composed by automatons or Homo sapiens. To tackle this problem, we apply a masked language model based on ALBERT for composers classification. The aim is to obtain a model that can suggest the probability a MIDI clip might be composed condition on the auto-generation hypothesis, and which is trained with only AI-composed single-track MIDI. In this paper, the amount of parameters is reduced, two methods on data augmentation are…
Automatic Chord Estimation (ACE) is a fundamental task in Music Information Retrieval (MIR) and has applications in both music performance and MIR research. The task consists of segmenting a music recording or score and assigning a chord label to each segment. Although it has been a task in the annual benchmarking evaluation MIREX for over 10 years, ACE is not yet a solved problem, since performance has stagnated and modern systems have started to tune themselves to subjective training data. We propose DECIBEL, a new ACE system that exploits widely available MIDI and tab representations to imp…
University of Crete（克里特大学）；Institute of Computer Science, FORTH-ICS（希腊研究与技术基金会计算机科学研究所）
This paper introduces a simple method for producing multichannel MIDI music that is based on randomness and simple probabilities. One distinctive feature of the method is that it produces and sends in parallel to the sound card more than one unsynchronized channels by exploiting the multi-threading capabilities of general purpose programming languages. As consequence the derived sound offers a quite ``full" and ``unpredictable" acoustic experience to the listener. Subsequently the paper reports the results of an evaluation with users. The results were very surprising: the majority of users res…
The paper presents a method of the music generation based on LSTM (Long Short-Term Memory), contrasts the effects of different network structures on the music generation and introduces other methods used by some researchers.
This study focuses on the perception of music performances when contextual factors, such as room acoustics and instrument, change. We propose to distinguish the concept of "performance" from the one of "interpretation", which expresses the "artistic intention". Towards assessing this distinction, we carried out an experimental evaluation where 91 subjects were invited to listen to various audio recordings created by resynthesizing MIDI data obtained through Automatic Music Transcription (AMT) systems and a sensorized acoustic piano. During the resynthesis, we simulated different contexts and a…
Modelling human perception of musical similarity is critical for the evaluation of generative music systems, musicological research, and many Music Information Retrieval tasks. Although human similarity judgments are the gold standard, computational analysis is often preferable, since results are often easier to reproduce, and computational methods are much more scalable. Moreover, computation based approaches can be calculated quickly and on demand, which is a prerequisite for use with an online system. We propose StyleRank, a method to measure the similarity between a MIDI file and an arbitr…
Making a slight mistake during live music performance can easily be spotted by an astute listener, even if the performance is an improvisation or an unfamiliar piece. An example might be a highly dissonant chord played by mistake in a classical-era sonata, or a sudden off-key note in a recurring motif. The problem of identifying and correcting such errors can be approached with artificial intelligence -- if a trained human can easily do it, maybe a computer can be trained to spot the errors quickly and just as accurately. The ability to identify and auto-correct errors in real-time would be no…
A model of music needs to have the ability to recall past details and have a clear, coherent understanding of musical structure. Detailed in the paper is a neural network architecture that predicts and generates polyphonic music aligned with musical rules. The probabilistic model presented is a Bi-axial LSTM trained with a kernel reminiscent of a convolutional kernel. When analyzed quantitatively and qualitatively, this approach performs well in composing polyphonic music. Link to the code is provided.
This thesis is presenting a method for generating short musical phrases using a deep convolutional generative adversarial network (DCGAN). To train neural network were used datasets of classical and jazz music MIDI recordings. Our approach introduces translating the MIDI data into graphical images in a piano roll format suitable for the network input size, using the RGB channels as additional information carriers for improved performance. The network has learned to generate images that are indistinguishable from the input data and, when translated back to MIDI and played back, include several …
M6(GPT)3: Generating Multitrack Modifiable Multi-Minute MIDI Music from Text using Genetic algorithms, Probabilistic methods and GPT Models in any Progression and Time Signature
Institute of Computer Science（计算机科学研究院）；Warsaw University of Technology（华沙技术大学）；Department of Robotics and Decision Systems（机器人与决策系统系）；Gdansk University of Technology（格但斯克技术大学）
University of Southern California（南加州大学）；National Institute of Informatics（国立信息学研究所）
With the similarity between music and speech synthesis from symbolic input and the rapid development of text-to-speech (TTS) techniques, it is worthwhile to explore ways to improve the MIDI-to-audio performance by borrowing from TTS techniques. In this study, we analyze the shortcomings of a TTS-based MIDI-to-audio system and improve it in terms of feature computation, model selection, and training strategy, aiming to synthesize highly natural-sounding audio. Moreover, we conducted an extensive model evaluation through listening tests, pitch measurement, and spectrogram analysis. This work dem…
