Search

Western music is often characterized by a homophonic texture, in which the musical content can be organized into a melody and an accompaniment. In orchestral music, in particular, the composer can select specific characteristics for each instrument's part within the accompaniment, while also needing to adapt the melody to suit the capabilities of the instruments performing it. In this work, we propose METEOR, a model for Melody-aware Texture-controllable Orchestral music generation. This model performs symbolic multi-track music style transfer with a focus on melodic fidelity. We allow bar- and track-level controllability of the accompaniment with various textural attributes while keeping a homophonic texture. We show that the model can achieve controllability performances similar to strong baselines while greatly improve melodic fidelity., Comment: https://dinhviettoanle.github.io/meteor

Neural network models for guitar amplifier emulation, while being effective, often demand high computational cost and lack interpretability. Drawing ideas from physical amplifier design, this paper aims to address these issues with a new differentiable digital signal processing (DDSP)-based model, called ``DDSP guitar amp,'' that models the four components of a guitar amp (i.e., preamp, tone stack, power amp, and output transformer) using specific DSP-inspired designs. With a set of time- and frequency-domain metrics, we demonstrate that DDSP guitar amp achieves performance comparable with that of black-box baselines while requiring less than 10\% of the computational operations per audio sample, thereby holding greater potential for usages in real-time applications., Comment: Preprint paper

We present PyNeuralFx, an open-source Python toolkit designed for research on neural audio effect modeling. The toolkit provides an intuitive framework and offers a comprehensive suite of features, including standardized implementation of well-established model architectures, loss functions, and easy-to-use visualization tools. As such, it helps promote reproducibility for research on neural audio effect modeling, and enable in-depth performance comparison of different models, offering insight into the behavior and operational characteristics of models through DSP methodology. The toolkit can be found at https://github.com/ytsrt66589/pyneuralfx., Comment: toolkit paper

Recurrent neural networks (RNNs) have demonstrated impressive results for virtual analog modeling of audio effects. These networks process time-domain audio signals using a series of matrix multiplication and nonlinear activation functions to emulate the behavior of the target device accurately. To additionally model the effect of the knobs for an RNN-based model, existing approaches integrate control parameters by concatenating them channel-wisely with some intermediate representation of the input signal. While this method is parameter-efficient, there is room to further improve the quality of generated audio because the concatenation-based conditioning method has limited capacity in modulating signals. In this paper, we propose three novel conditioning mechanisms for RNNs, tailored for black-box virtual analog modeling. These advanced conditioning mechanisms modulate the model based on control parameters, yielding superior results to existing RNN- and CNN-based architectures across various evaluation metrics., Comment: Accepted to DAFx24

Piano cover generation aims to create a piano cover from a pop song. Existing approaches mainly employ supervised learning and the training demands strongly-aligned and paired song-to-piano data, which is built by remapping piano notes to song audio. This would, however, result in the loss of piano information and accordingly cause inconsistencies between the original and remapped piano versions. To overcome this limitation, we propose a transfer learning approach that pre-trains our model on piano-only data and fine-tunes it on weakly-aligned paired data constructed without note remapping. During pre-training, to guide the model to learn piano composition concepts instead of merely transcribing audio, we use an existing lead sheet transcription model as the encoder to extract high-level features from the piano recordings. The pre-trained model is then fine-tuned on the paired song-piano data to transfer the learned composition knowledge to the pop song domain. Our evaluation shows that this training strategy enables our model, named PiCoGen2, to attain high-quality results, outperforming baselines on both objective and subjective metrics across five pop genres., Comment: Accepted at the 25th International Society for Music Information Retrieval Conference (ISMIR), 2024

Managing the emotional aspect remains a challenge in automatic music generation. Prior works aim to learn various emotions at once, leading to inadequate modeling. This paper explores the disentanglement of emotions in piano performance generation through a two-stage framework. The first stage focuses on valence modeling of lead sheet, and the second stage addresses arousal modeling by introducing performance-level attributes. To further capture features that shape valence, an aspect less explored by previous approaches, we introduce a novel functional representation of symbolic music. This representation aims to capture the emotional impact of major-minor tonality, as well as the interactions among notes, chords, and key signatures. Objective and subjective experiments validate the effectiveness of our framework in both emotional valence and arousal modeling. We further leverage our framework in a novel application of emotional controls, showing a broad potential in emotion-driven music generation., Comment: Proceedings of the 25th International Society for Music Information Retrieval Conference, ISMIR 2024

Cover song generation stands out as a popular way of music making in the music-creative community. In this study, we introduce Piano Cover Generation (PiCoGen), a two-stage approach for automatic cover song generation that transcribes the melody line and chord progression of a song given its audio recording, and then uses the resulting lead sheet as the condition to generate a piano cover in the symbolic domain. This approach is advantageous in that it does not required paired data of covers and their original songs for training. Compared to an existing approach that demands such paired data, our evaluation shows that PiCoGen demonstrates competitive or even superior performance across songs of different musical genres., Comment: Published at ICMR 2024 (project page: https://tanchihpin0517.github.io/PiCoGen/)

Emotion-driven melody harmonization aims to generate diverse harmonies for a single melody to convey desired emotions. Previous research found it hard to alter the perceived emotional valence of lead sheets only by harmonizing the same melody with different chords, which may be attributed to the constraints imposed by the melody itself and the limitation of existing music representation. In this paper, we propose a novel functional representation for symbolic music. This new method takes musical keys into account, recognizing their significant role in shaping music's emotional character through major-minor tonality. It also allows for melodic variation with respect to keys and addresses the problem of data scarcity for better emotion modeling. A Transformer is employed to harmonize key-adaptable melodies, allowing for keys determined in rule-based or model-based manner. Experimental results confirm the effectiveness of our new representation in generating key-aware harmonies, with objective and subjective evaluations affirming the potential of our approach to convey specific valence for versatile melody., Comment: This work is the initial version of the ISMIR 2024 paper EMO-Disentanger

Removing audio effects from electric guitar recordings makes it easier for post-production and sound editing. An audio distortion recovery model not only improves the clarity of the guitar sounds but also opens up new opportunities for creative adjustments in mixing and mastering. While progress have been made in creating such models, previous efforts have largely focused on synthetic distortions that may be too simplistic to accurately capture the complexities seen in real-world recordings. In this paper, we tackle the task by using a dataset of guitar recordings rendered with commercial-grade audio effect VST plugins. Moreover, we introduce a novel two-stage methodology for audio distortion recovery. The idea is to firstly process the audio signal in the Mel-spectrogram domain in the first stage, and then use a neural vocoder to generate the pristine original guitar sound from the processed Mel-spectrogram in the second stage. We report a set of experiments demonstrating the effectiveness of our approach over existing methods, through both subjective and objective evaluation metrics., Comment: DAFx 2024

Text-to-music models allow users to generate nearly realistic musical audio with textual commands. However, editing music audios remains challenging due to the conflicting desiderata of performing fine-grained alterations on the audio while maintaining a simple user interface. To address this challenge, we propose Audio Prompt Adapter (or AP-Adapter), a lightweight addition to pretrained text-to-music models. We utilize AudioMAE to extract features from the input audio, and construct attention-based adapters to feedthese features into the internal layers of AudioLDM2, a diffusion-based text-to-music model. With 22M trainable parameters, AP-Adapter empowers users to harness both global (e.g., genre and timbre) and local (e.g., melody) aspects of music, using the original audio and a short text as inputs. Through objective and subjective studies, we evaluate AP-Adapter on three tasks: timbre transfer, genre transfer, and accompaniment generation. Additionally, we demonstrate its effectiveness on out-of-domain audios containing unseen instruments during training., Comment: Accepted by the 25th International Society for Music Information Retrieval (ISMIR)

Existing text-to-music models can produce high-quality audio with great diversity. However, textual prompts alone cannot precisely control temporal musical features such as chords and rhythm of the generated music. To address this challenge, we introduce MusiConGen, a temporally-conditioned Transformer-based text-to-music model that builds upon the pretrained MusicGen framework. Our innovation lies in an efficient finetuning mechanism, tailored for consumer-grade GPUs, that integrates automatically-extracted rhythm and chords as the condition signal. During inference, the condition can either be musical features extracted from a reference audio signal, or be user-defined symbolic chord sequence, BPM, and textual prompts. Our performance evaluation on two datasets -- one derived from extracted features and the other from user-created inputs -- demonstrates that MusiConGen can generate realistic backing track music that aligns well with the specified conditions. We open-source the code and model checkpoints, and provide audio examples online, https://musicongen.github.io/musicongen_demo/., Comment: Accepted by the 25th International Society for Music Information Retrieval (ISMIR)

Replicating analog device circuits through neural audio effect modeling has garnered increasing interest in recent years. Existing work has predominantly focused on a one-to-one emulation strategy, modeling specific devices individually. In this paper, we tackle the less-explored scenario of one-to-many emulation, utilizing conditioning mechanisms to emulate multiple guitar amplifiers through a single neural model. For condition representation, we use contrastive learning to build a tone embedding encoder that extracts style-related features of various amplifiers, leveraging a dataset of comprehensive amplifier settings. Targeting zero-shot application scenarios, we also examine various strategies for tone embedding representation, evaluating referenced tone embedding against two retrieval-based embedding methods for amplifiers unseen in the training time. Our findings showcase the efficacy and potential of the proposed methods in achieving versatile one-to-many amplifier modeling, contributing a foundational step towards zero-shot audio modeling applications., Comment: ISMIR 2024

Recent years have seen increasing interest in applying deep learning methods to the modeling of guitar amplifiers or effect pedals. Existing methods are mainly based on the supervised approach, requiring temporally-aligned data pairs of unprocessed and rendered audio. However, this approach does not scale well, due to the complicated process involved in creating the data pairs. A very recent work done by Wright et al. has explored the potential of leveraging unpaired data for training, using a generative adversarial network (GAN)-based framework. This paper extends their work by using more advanced discriminators in the GAN, and using more unpaired data for training. Specifically, drawing inspiration from recent advancements in neural vocoders, we employ in our GAN-based model for guitar amplifier modeling two sets of discriminators, one based on multi-scale discriminator (MSD) and the other multi-period discriminator (MPD). Moreover, we experiment with adding unprocessed audio signals that do not have the corresponding rendered audio of a target tone to the training data, to see how much the GAN model benefits from the unpaired data. Our experiments show that the proposed two extensions contribute to the modeling of both low-gain and high-gain guitar amplifiers., Comment: Accepted to DAFx 2024

In this article, we investigate the notion of model-based deep learning in the realm of music information research (MIR). Loosely speaking, we refer to the term model-based deep learning for approaches that combine traditional knowledge-based methods with data-driven techniques, especially those based on deep learning, within a diff erentiable computing framework. In music, prior knowledge for instance related to sound production, music perception or music composition theory can be incorporated into the design of neural networks and associated loss functions. We outline three specifi c scenarios to illustrate the application of model-based deep learning in MIR, demonstrating the implementation of such concepts and their potential., Comment: IEEE Signal Processing Magazine, In press

To model the periodicity of beats, state-of-the-art beat tracking systems use "post-processing trackers" (PPTs) that rely on several empirically determined global assumptions for tempo transition, which work well for music with a steady tempo. For expressive classical music, however, these assumptions can be too rigid. With two large datasets of Western classical piano music, namely the Aligned Scores and Performances (ASAP) dataset and a dataset of Chopin's Mazurkas (Maz-5), we report on experiments showing the failure of existing PPTs to cope with local tempo changes, thus calling for new methods. In this paper, we propose a new local periodicity-based PPT, called predominant local pulse-based dynamic programming (PLPDP) tracking, that allows for more flexible tempo transitions. Specifically, the new PPT incorporates a method called "predominant local pulses" (PLP) in combination with a dynamic programming (DP) component to jointly consider the locally detected periodicity and beat activation strength at each time instant. Accordingly, PLPDP accounts for the local periodicity, rather than relying on a global tempo assumption. Compared to existing PPTs, PLPDP particularly enhances the recall values at the cost of a lower precision, resulting in an overall improvement of F1-score for beat tracking in ASAP (from 0.473 to 0.493) and Maz-5 (from 0.595 to 0.838)., Comment: Accepted to IEEE/ACM Transactions on Audio, Speech, and Language Processing (July 2023)

For expressive music, the tempo may change over time, posing challenges to tracking the beats by an automatic model. The model may first tap to the correct tempo, but then may fail to adapt to a tempo change, or switch between several incorrect but perceptually plausible ones (e.g., half- or double-tempo). Existing evaluation metrics for beat tracking do not reflect such behaviors, as they typically assume a fixed relationship between the reference beats and estimated beats. In this paper, we propose a new performance analysis method, called annotation coverage ratio (ACR), that accounts for a variety of possible metric-level switching behaviors of beat trackers. The idea is to derive sequences of modified reference beats of all metrical levels for every two consecutive reference beats, and compare every sequence of modified reference beats to the subsequences of estimated beats. We show via experiments on three datasets of different genres the usefulness of ACR when utilized alongside existing metrics, and discuss the new insights to be gained., Comment: Accepted to IEEE Signal Processing Letters (Oct. 2022)

This paper proposes a model that generates a drum track in the audio domain to play along to a user-provided drum-free recording. Specifically, using paired data of drumless tracks and the corresponding human-made drum tracks, we train a Transformer model to improvise the drum part of an unseen drumless recording. We combine two approaches to encode the input audio. First, we train a vector-quantized variational autoencoder (VQ-VAE) to represent the input audio with discrete codes, which can then be readily used in a Transformer. Second, using an audio-domain beat tracking model, we compute beat-related features of the input audio and use them as embeddings in the Transformer. Instead of generating the drum track directly as waveforms, we use a separate VQ-VAE to encode the mel-spectrogram of a drum track into another set of discrete codes, and train the Transformer to predict the sequence of drum-related discrete codes. The output codes are then converted to a mel-spectrogram with a decoder, and then to the waveform with a vocoder. We report both objective and subjective evaluations of variants of the proposed model, demonstrating that the model with beat information generates drum accompaniment that is rhythmically and stylistically consistent with the input audio., Comment: Accepted at ISMIR 2022

This paper proposes a novel Transformer-based model for music score infilling, to generate a music passage that fills in the gap between given past and future contexts. While existing infilling approaches can generate a passage that connects smoothly locally with the given contexts, they do not take into account the musical form or structure of the music and may therefore generate overly smooth results. To address this issue, we propose a structure-aware conditioning approach that employs a novel attention-selecting module to supply user-provided structure-related information to the Transformer for infilling. With both objective and subjective evaluations, we show that the proposed model can harness the structural information effectively and generate melodies in the style of pop of higher quality than the two existing structure-agnostic infilling models.

Even with strong sequence models like Transformers, generating expressive piano performances with long-range musical structures remains challenging. Meanwhile, methods to compose well-structured melodies or lead sheets (melody + chords), i.e., simpler forms of music, gained more success. Observing the above, we devise a two-stage Transformer-based framework that Composes a lead sheet first, and then Embellishes it with accompaniment and expressive touches. Such a factorization also enables pretraining on non-piano data. Our objective and subjective experiments show that Compose & Embellish shrinks the gap in structureness between a current state of the art and real performances by half, and improves other musical aspects such as richness and coherence as well., Comment: Accepted to International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2023

While generative adversarial networks (GANs) have been widely used in research on audio generation, the training of a GAN model is known to be unstable, time consuming, and data inefficient. Among the attempts to ameliorate the training process of GANs, the idea of Projected GAN emerges as an effective solution for GAN-based image generation, establishing the state-of-the-art in different image applications. The core idea is to use a pre-trained classifier to constrain the feature space of the discriminator to stabilize and improve GAN training. This paper investigates whether Projected GAN can similarly improve audio generation, by evaluating the performance of a StyleGAN2-based audio-domain loop generation model with and without using a pre-trained feature space in the discriminator. Moreover, we compare the performance of using a general versus domain-specific classifier as the pre-trained audio classifier. With experiments on both drum loop and synth loop generation, we show that a general audio classifier works better, and that with Projected GAN our loop generation models can converge around 5 times faster without performance degradation., Comment: Accepted at ISMIR 2022

A vocoder is a conditional audio generation model that converts acoustic features such as mel-spectrograms into waveforms. Taking inspiration from Differentiable Digital Signal Processing (DDSP), we propose a new vocoder named SawSing for singing voices. SawSing synthesizes the harmonic part of singing voices by filtering a sawtooth source signal with a linear time-variant finite impulse response filter whose coefficients are estimated from the input mel-spectrogram by a neural network. As this approach enforces phase continuity, SawSing can generate singing voices without the phase-discontinuity glitch of many existing vocoders. Moreover, the source-filter assumption provides an inductive bias that allows SawSing to be trained on a small amount of data. Our experiments show that SawSing converges much faster and outperforms state-of-the-art generative adversarial network and diffusion-based vocoders in a resource-limited scenario with only 3 training recordings and a 3-hour training time., Comment: Accepted at ISMIR 2022

In this paper, we propose a new dataset named EGDB, that con-tains transcriptions of the electric guitar performance of 240 tab-latures rendered with different tones. Moreover, we benchmark theperformance of two well-known transcription models proposed orig-inally for the piano on this dataset, along with a multi-loss Trans-former model that we newly propose. Our evaluation on this datasetand a separate set of real-world recordings demonstrate the influenceof timbre on the accuracy of guitar sheet transcription, the potentialof using multiple losses for Transformers, as well as the room forfurther improvement for this task., Comment: to be published at ICASSP 2022

In this paper, we investigate using the variable-length infilling (VLI) model, which is originally proposed to infill missing segments, to "prolong" existing musical segments at musical boundaries. Specifically, as a case study, we expand 20 musical segments from 12 bars to 16 bars, and examine the degree to which the VLI model preserves musical boundaries in the expanded results using a few objective metrics, including the Register Histogram Similarity we newly propose. The results show that the VLI model has the potential to address the expansion task., Comment: Going to published as a late-breaking demo paper at ISMIR 2021

Attention-based Transformer models have been increasingly employed for automatic music generation. To condition the generation process of such a model with a user-specified sequence, a popular approach is to take that conditioning sequence as a priming sequence and ask a Transformer decoder to generate a continuation. However, this prompt-based conditioning cannot guarantee that the conditioning sequence would develop or even simply repeat itself in the generated continuation. In this paper, we propose an alternative conditioning approach, called theme-based conditioning, that explicitly trains the Transformer to treat the conditioning sequence as a thematic material that has to manifest itself multiple times in its generation result. This is achieved with two main technical contributions. First, we propose a deep learning-based approach that uses contrastive representation learning and clustering to automatically retrieve thematic materials from music pieces in the training data. Second, we propose a novel gated parallel attention module to be used in a sequence-to-sequence (seq2seq) encoder/decoder architecture to more effectively account for a given conditioning thematic material in the generation process of the Transformer decoder. We report on objective and subjective evaluations of variants of the proposed Theme Transformer and the conventional prompt-based baseline, showing that our best model can generate, to some extent, polyphonic pop piano music with repetition and plausible variations of a given condition., Comment: to be published at IEEE Transactions on Multimedia

Recent years have witnessed a growing interest in research related to the detection of piano pedals from audio signals in the music information retrieval community. However, to our best knowledge, recent generative models for symbolic music have rarely taken piano pedals into account. In this work, we employ the transcription model proposed by Kong et al. to get pedal information from the audio recordings of piano performance in the AILabs1k7 dataset, and then modify the Compound Word Transformer proposed by Hsiao et al. to build a Transformer decoder that generates pedal-related tokens along with other musical tokens. While the work is done by using inferred sustain pedal information as training data, the result shows hope for further improvement and the importance of the involvement of sustain pedal in tasks of piano performance generations.

Along with the evolution of music technology, a large number of styles, or "subgenres," of Electronic Dance Music(EDM) have emerged in recent years. While the classification task of distinguishing between EDM and non-EDM has been often studied in the context of music genre classification, little work has been done on the more challenging EDM subgenre classification. The state-of-art model is based on extremely randomized trees and could be improved by deep learning methods. In this paper, we extend the state-of-art music auto-tagging model "short-chunkCNN+Resnet" to EDM subgenre classification, with the addition of two mid-level tempo-related feature representations, called the Fourier tempogram and autocorrelation tempogram. And, we explore two fusion strategies, early fusion and late fusion, to aggregate the two types of tempograms. We evaluate the proposed models using a large dataset consisting of 75,000 songs for 30 different EDM subgenres, and show that the adoption of deep learning models and tempo features indeed leads to higher classification accuracy.

A central task of a Disc Jockey (DJ) is to create a mixset of mu-sic with seamless transitions between adjacent tracks. In this paper, we explore a data-driven approach that uses a generative adversarial network to create the song transition by learning from real-world DJ mixes. In particular, the generator of the model uses two differentiable digital signal processing components, an equalizer (EQ) and a fader, to mix two tracks selected by a data generation pipeline. The generator has to set the parameters of the EQs and fader in such away that the resulting mix resembles real mixes created by humanDJ, as judged by the discriminator counterpart. Result of a listening test shows that the model can achieve competitive results compared with a number of baselines., Comment: To be published at ICASSP 2022

In this paper, we propose a novel neural network model called KaraSinger for a less-studied singing voice synthesis (SVS) task named score-free SVS, in which the prosody and melody are spontaneously decided by machine. KaraSinger comprises a vector-quantized variational autoencoder (VQ-VAE) that compresses the Mel-spectrograms of singing audio to sequences of discrete codes, and a language model (LM) that learns to predict the discrete codes given the corresponding lyrics. For the VQ-VAE part, we employ a Connectionist Temporal Classification (CTC) loss to encourage the discrete codes to carry phoneme-related information. For the LM part, we use location-sensitive attention for learning a robust alignment between the input phoneme sequence and the output discrete code. We keep the architecture of both the VQ-VAE and LM light-weight for fast training and inference speed. We validate the effectiveness of the proposed design choices using a proprietary collection of 550 English pop songs sung by multiple amateur singers. The result of a listening test shows that KaraSinger achieves high scores in intelligibility, musicality, and the overall quality., Comment: Submitted to ICASSP 2022

This paper proposes a new self-attention based model for music score infilling, i.e., to generate a polyphonic music sequence that fills in the gap between given past and future contexts. While existing approaches can only fill in a short segment with a fixed number of notes, or a fixed time span between the past and future contexts, our model can infill a variable number of notes (up to 128) for different time spans. We achieve so with three major technical contributions. First, we adapt XLNet, an autoregressive model originally proposed for unsupervised model pre-training, to music score infilling. Second, we propose a new, musically specialized positional encoding called relative bar encoding that better informs the model of notes' position within the past and future context. Third, to capitalize relative bar encoding, we perform look-ahead onset prediction to predict the onset of a note one time step before predicting the other attributes of the note. We compare our proposed model with two strong baselines and show that our model is superior in both objective and subjective analyses., Comment: The paper has been accepted for publication at ISMIR 2021

This paper proposes a new benchmark task for generat-ing musical passages in the audio domain by using thedrum loops from the FreeSound Loop Dataset, which arepublicly re-distributable. Moreover, we use a larger col-lection of drum loops from Looperman to establish fourmodel-based objective metrics for evaluation, releasingthese metrics as a library for quantifying and facilitatingthe progress of musical audio generation. Under this eval-uation framework, we benchmark the performance of threerecent deep generative adversarial network (GAN) mod-els we customize to generate loops, including StyleGAN,StyleGAN2, and UNAGAN. We also report a subjectiveevaluation of these models. Our evaluation shows that theone based on StyleGAN2 performs the best in both objec-tive and subjective metrics., Comment: The paper has been accepted for publication at ISMIR 2021

While there are many music datasets with emotion labels in the literature, they cannot be used for research on symbolic-domain music analysis or generation, as there are usually audio files only. In this paper, we present the EMOPIA (pronounced `yee-m\`{o}-pi-uh') dataset, a shared multi-modal (audio and MIDI) database focusing on perceived emotion in pop piano music, to facilitate research on various tasks related to music emotion. The dataset contains 1,087 music clips from 387 songs and clip-level emotion labels annotated by four dedicated annotators. Since the clips are not restricted to one clip per song, they can also be used for song-level analysis. We present the methodology for building the dataset, covering the song list curation, clip selection, and emotion annotation processes. Moreover, we prototype use cases on clip-level music emotion classification and emotion-based symbolic music generation by training and evaluating corresponding models using the dataset. The result demonstrates the potential of EMOPIA for being used in future exploration on piano emotion-related MIR tasks., Comment: The paper has been accepted for publication at ISMIR 2021

Originating in the Renaissance and burgeoning in the digital era, tablatures are a commonly used music notation system which provides explicit representations of instrument fingerings rather than pitches. GuitarPro has established itself as a widely used tablature format and software enabling musicians to edit and share songs for musical practice, learning, and composition. In this work, we present DadaGP, a new symbolic music dataset comprising 26,181 song scores in the GuitarPro format covering 739 musical genres, along with an accompanying tokenized format well-suited for generative sequence models such as the Transformer. The tokenized format is inspired by event-based MIDI encodings, often used in symbolic music generation models. The dataset is released with an encoder/decoder which converts GuitarPro files to tokens and back. We present results of a use case in which DadaGP is used to train a Transformer-based model to generate new songs in GuitarPro format. We discuss other relevant use cases for the dataset (guitar-bass transcription, music style transfer and artist/genre classification) as well as ethical implications. DadaGP opens up the possibility to train GuitarPro score generators, fine-tune models on custom data, create new styles of music, AI-powered songwriting apps, and human-AI improvisation.

This article presents a benchmark study of symbolic piano music classification using the masked language modelling approach of the Bidirectional Encoder Representations from Transformers (BERT). Specifically, we consider two types of MIDI data: MIDI scores, which are musical scores rendered directly into MIDI with no dynamics and precisely aligned with the metrical grid notated by its composer and MIDI performances, which are MIDI encodings of human performances of musical scoresheets. With five public-domain datasets of single-track piano MIDI files, we pre-train two 12-layer Transformer models using the BERT approach, one for MIDI scores and the other for MIDI performances, and fine-tune them for four downstream classification tasks. These include two note-level classification tasks (melody extraction and velocity prediction) and two sequence-level classification tasks (style classification and emotion classification). Our evaluation shows that the BERT approach leads to higher classification accuracy than recurrent neural network (RNN)-based baselines., Comment: Accepted to Journal of Creative Music Systems

Due to advances in deep learning, the performance of automatic beat and downbeat tracking in musical audio signals has seen great improvement in recent years. In training such deep learning based models, data augmentation has been found an important technique. However, existing data augmentation methods for this task mainly target at balancing the distribution of the training data with respect to their tempo. In this paper, we investigate another approach for data augmentation, to account for the composition of the training data in terms of the percussive and non-percussive sound sources. Specifically, we propose to employ a blind drum separation model to segregate the drum and non-drum sounds from each training audio signal, filtering out training signals that are drumless, and then use the obtained drum and non-drum stems to augment the training data. We report experiments on four completely unseen test sets, validating the effectiveness of the proposed method, and accordingly the importance of drum sound composition in the training data for beat and downbeat tracking., Comment: Accepted to European Signal Processing Conference (EUSIPCO 2021)

This paper presents a novel system architecture that integrates blind source separation with joint beat and downbeat tracking in musical audio signals. The source separation module segregates the percussive and non-percussive components of the input signal, over which beat and downbeat tracking are performed separately and then the results are aggregated with a learnable fusion mechanism. This way, the system can adaptively determine how much the tracking result for an input signal should depend on the input's percussive or non-percussive components. Evaluation on four testing sets that feature different levels of presence of drum sounds shows that the new architecture consistently outperforms the widely-adopted baseline architecture that does not employ source separation., Comment: Accepted to IEEE Signal Processing Letters (May 2021)

Recent advances in Transformer models allow for unprecedented sequence lengths, due to linear space and time complexity. In the meantime, relative positional encoding (RPE) was proposed as beneficial for classical Transformers and consists in exploiting lags instead of absolute positions for inference. Still, RPE is not available for the recent linear-variants of the Transformer, because it requires the explicit computation of the attention matrix, which is precisely what is avoided by such methods. In this paper, we bridge this gap and present Stochastic Positional Encoding as a way to generate PE that can be used as a replacement to the classical additive (sinusoidal) PE and provably behaves like RPE. The main theoretical contribution is to make a connection between positional encoding and cross-covariance structures of correlated Gaussian processes. We illustrate the performance of our approach on the Long-Range Arena benchmark and on music generation., Comment: ICML 2021 (long talk) camera-ready. 24 pages

Transformers and variational autoencoders (VAE) have been extensively employed for symbolic (e.g., MIDI) domain music generation. While the former boast an impressive capability in modeling long sequences, the latter allow users to willingly exert control over different parts (e.g., bars) of the music to be generated. In this paper, we are interested in bringing the two together to construct a single model that exhibits both strengths. The task is split into two steps. First, we equip Transformer decoders with the ability to accept segment-level, time-varying conditions during sequence generation. Subsequently, we combine the developed and tested in-attention decoder with a Transformer encoder, and train the resulting MuseMorphose model with the VAE objective to achieve style transfer of long pop piano pieces, in which users can specify musical attributes including rhythmic intensity and polyphony (i.e., harmonic fullness) they desire, down to the bar level. Experiments show that MuseMorphose outperforms recurrent neural network (RNN) based baselines on numerous widely-used metrics for style transfer tasks., Comment: Accepted for Publication at IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP). Online supplemental materials are attached to the end of this arXiv version

To apply neural sequence models such as the Transformers to music generation tasks, one has to represent a piece of music by a sequence of tokens drawn from a finite set of pre-defined vocabulary. Such a vocabulary usually involves tokens of various types. For example, to describe a musical note, one needs separate tokens to indicate the note's pitch, duration, velocity (dynamics), and placement (onset time) along the time grid. While different types of tokens may possess different properties, existing models usually treat them equally, in the same way as modeling words in natural languages. In this paper, we present a conceptually different approach that explicitly takes into account the type of the tokens, such as note types and metric types. And, we propose a new Transformer decoder architecture that uses different feed-forward heads to model tokens of different types. With an expansion-compression trick, we convert a piece of music to a sequence of compound words by grouping neighboring tokens, greatly reducing the length of the token sequences. We show that the resulting model can be viewed as a learner over dynamic directed hypergraphs. And, we employ it to learn to compose expressive Pop piano music of full-song length (involving up to 10K individual tokens per song), both conditionally and unconditionally. Our experiment shows that, compared to state-of-the-art models, the proposed model converges 5--10 times faster at training (i.e., within a day on a single GPU with 11 GB memory), and with comparable quality in the generated music.

Music loops are essential ingredients in electronic music production, and there is a high demand for pre-recorded loops in a variety of styles. Several commercial and community databases have been created to meet this demand, but most are not suitable for research due to their strict licensing. We present the Freesound Loop Dataset (FSLD), a new large-scale dataset of music loops annotated by experts. The loops originate from Freesound, a community database of audio recordings released under Creative Commons licenses, so the audio in our dataset may be redistributed. The annotations include instrument, tempo, meter, key and genre tags. We describe the methodology used to assemble and annotate the data, and report on the distribution of tags in the data and inter-annotator agreement. We also present to the community an online loop annotator tool that we developed. To illustrate the usefulness of FSLD, we present short case studies on using it to estimate tempo and key, generate music tracks, and evaluate a loop separation algorithm. We anticipate that the community will find yet more uses for the data, in applications from automatic loop characterisation to algorithmic composition., Comment: This work will be presented in the 21st International Society for Music Information Retrieval (ISMIR2020). Annotator website: http://mtg.upf.edu/fslannotator Dataset: https://zenodo.org/record/3967852

A DJ mix is a sequence of music tracks concatenated seamlessly, typically rendered for audiences in a live setting by a DJ on stage. As a DJ mix is produced in a studio or the live version is recorded for music streaming services, computational methods to analyze DJ mixes, for example, extracting track information or understanding DJ techniques, have drawn research interests. Many of previous works are, however, limited to identifying individual tracks in a mix or segmenting it, and the sizes of the datasets are usually small. In this paper, we provide an in-depth analysis of DJ music by aligning a mix to its original music tracks. We set up the subsequence alignment such that the audio features are less sensitive to the tempo or key change of the original track in a mix. This approach provides temporally tight mix-to-track matching from which we can obtain cue-points, transition length, mix segmentation, and musical changes in DJ performance. Using 1,557 mixes from 1001Tracklists including 13,728 tracks and 20,765 transitions, we conduct the proposed analysis and show a wide range of statistics, which may elucidate the creative process of DJ music making., Comment: Accepted for publication at 21st International Society for Music Information Retrieval Conference (ISMIR 2020)

Blind music source separation has been a popular and active subject of research in both the music information retrieval and signal processing communities. To counter the lack of available multi-track data for supervised model training, a data augmentation method that creates artificial mixtures by combining tracks from different songs has been shown useful in recent works. Following this light, we examine further in this paper extended data augmentation methods that consider more sophisticated mixing settings employed in the modern music production routine, the relationship between the tracks to be combined, and factors of silence. As a case study, we consider the separation of violin and piano tracks in a violin piano ensemble, evaluating the performance in terms of common metrics, namely SDR, SIR, and SAR. In addition to examining the effectiveness of these new data augmentation methods, we also study the influence of the amount of training data. Our evaluation shows that the proposed mixing-specific data augmentation methods can help improve the performance of a deep learning-based model for source separation, especially in the case of small training data., Comment: Accepted to IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP 2020)

Music producers who use loops may have access to thousands in loop libraries, but finding ones that are compatible is a time-consuming process; we hope to reduce this burden with automation. State-of-the-art systems for estimating compatibility, such as AutoMashUpper, are mostly rule-based and could be improved on with machine learn-ing. To train a model, we need a large set of loops with ground truth compatibility values. No such dataset exists, so we extract loops from existing music to obtain positive examples of compatible loops, and propose and compare various strategies for choosing negative examples. For re-producibility, we curate data from the Free Music Archive.Using this data, we investigate two types of model architectures for estimating the compatibility of loops: one based on a Siamese network, and the other a pure convolutional neural network (CNN). We conducted a user study in which participants rated the quality of the combinations suggested by each model, and found the CNN to outperform the Siamese network. Both model-based approaches outperformed the rule-based one. We have opened source the code for building the models and the dataset., Comment: Accepted to the 21st International Society for Music Information Retrieval Conference (ISMIR 2020)

Deep learning algorithms are increasingly developed for learning to compose music in the form of MIDI files. However, whether such algorithms work well for composing guitar tabs, which are quite different from MIDIs, remain relatively unexplored. To address this, we build a model for composing fingerstyle guitar tabs with Transformer-XL, a neural sequence model architecture. With this model, we investigate the following research questions. First, whether the neural net generates note sequences with meaningful note-string combinations, which is important for the guitar but not other instruments such as the piano. Second, whether it generates compositions with coherent rhythmic groove, crucial for fingerstyle guitar music. And, finally, how pleasant the composed music is in comparison to real, human-made compositions. Our work provides preliminary empirical evidence of the promise of deep learning for tab composition, and suggests areas for future study., Comment: Accepted at Proc. Int. Society for Music Information Retrieval Conf. 2020

This paper presents the Jazz Transformer, a generative model that utilizes a neural sequence model called the Transformer-XL for modeling lead sheets of Jazz music. Moreover, the model endeavors to incorporate structural events present in the Weimar Jazz Database (WJazzD) for inducing structures in the generated music. While we are able to reduce the training loss to a low value, our listening test suggests however a clear gap between the average ratings of the generated and real compositions. We therefore go one step further and conduct a series of computational analysis of the generated compositions from different perspectives. This includes analyzing the statistics of the pitch class, grooving, and chord progression, assessing the structureness of the music with the help of the fitness scape plot, and evaluating the model's understanding of Jazz music through a MIREX-like continuation prediction task. Our work presents in an analytical manner why machine-generated music to date still falls short of the artwork of humanity, and sets some goals for future work on automatic composition to further pursue., Comment: Accepted to the 21st International Society for Music Information Retrieval Conference (ISMIR 2020)

This paper investigates the use of generative adversarial network (GAN)-based models for converting the spectrogram of a speech signal into that of a singing one, without reference to the phoneme sequence underlying the speech. This is achieved by viewing speech-to-singing conversion as a style transfer problem. Specifically, given a speech input, and optionally the F0 contour of the target singing, the proposed model generates as the output a singing signal with a progressive-growing encoder/decoder architecture and boundary equilibrium GAN loss functions. Our quantitative and qualitative analysis show that the proposed model generates singing voices with much higher naturalness than an existing non adversarially-trained baseline. For reproducibility, the code will be publicly available at a GitHub repository upon paper publication., Comment: Accepted for publication at INTERSPEECH 2020

In a recent paper, we have presented a generative adversarial network (GAN)-based model for unconditional generation of the mel-spectrograms of singing voices. As the generator of the model is designed to take a variable-length sequence of noise vectors as input, it can generate mel-spectrograms of variable length. However, our previous listening test shows that the quality of the generated audio leaves room for improvement. The present paper extends and expands that previous work in the following aspects. First, we employ a hierarchical architecture in the generator to induce some structure in the temporal dimension. Second, we introduce a cycle regularization mechanism to the generator to avoid mode collapse. Third, we evaluate the performance of the new model not only for generating singing voices, but also for generating speech voices. Evaluation result shows that new model outperforms the prior one both objectively and subjectively. We also employ the model to unconditionally generate sequences of piano and violin music and find the result promising. Audio examples, as well as the code for implementing our model, will be publicly available online upon paper publication.

Whether literally or suggestively, the concept of soundscape is alluded in both modern and ancient music. In this study, we examine whether we can analyze and compare Western and Chinese classical music based on soundscape models. We addressed this question through a comparative study. Specifically, corpora of Western classical music excerpts (WCMED) and Chinese classical music excerpts (CCMED) were curated and annotated with emotional valence and arousal through a crowdsourcing experiment. We used a sound event detection (SED) and soundscape emotion recognition (SER) models with transfer learning to predict the perceived emotion of WCMED and CCMED. The results show that both SER and SED models could be used to analyze Chinese and Western classical music. The fact that SER and SED work better on Chinese classical music emotion recognition provides evidence that certain similarities exist between Chinese classical music and soundscape recordings, which permits transferability between machine learning models., Comment: Paper accepted for 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2020)

Identifying singers is an important task with many applications. However, the task remains challenging due to many issues. One major issue is related to the confounding factors from the background instrumental music that is mixed with the vocals in music production. A singer identification model may learn to extract non-vocal related features from the instrumental part of the songs, if a singer only sings in certain musical contexts (e.g., genres). The model cannot therefore generalize well when the singer sings in unseen contexts. In this paper, we attempt to address this issue. Specifically, we employ open-unmix, an open source tool with state-of-the-art performance in source separation, to separate the vocal and instrumental tracks of music. We then investigate two means to train a singer identification model: by learning from the separated vocal only, or from an augmented set of data where we "shuffle-and-remix" the separated vocal tracks and instrumental tracks of different songs to artificially make the singers sing in different contexts. We also incorporate melodic features learned from the vocal melody contour for better performance. Evaluation results on a benchmark dataset called the artist20 shows that this data augmentation method greatly improves the accuracy of singer identification.