DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Models
- URL: http://arxiv.org/abs/2107.14653v1
- Date: Fri, 30 Jul 2021 14:21:36 GMT
- Title: DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Models
- Authors: Pedro Sarmento, Adarsh Kumar, CJ Carr, Zack Zukowski, Mathieu Barthet,
Yi-Hsuan Yang
- Abstract summary: DadaGP is a new symbolic music dataset comprising 26,181 song scores in the GuitarPro format covering 739 musical genres.
DadaGP 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.
- Score: 25.15855175804765
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- MIDI-to-Tab: Guitar Tablature Inference via Masked Language Modeling [6.150307957212576]
We introduce a novel deep learning solution to symbolic guitar tablature estimation.
We train an encoder-decoder Transformer model in a masked language modeling paradigm to assign notes to strings.
The model is first pre-trained on DadaGP, a dataset of over 25K tablatures, and then fine-tuned on a curated set of professionally transcribed guitar performances.
arXiv Detail & Related papers (2024-08-09T12:25:23Z) - A Novel Bi-LSTM And Transformer Architecture For Generating Tabla Music [2.062778014412626]
Methods for generating classical Indian music, specifically tabla music, is proposed.
A novel Bi-LSTM with an Attention approach and a transformer model are trained on the extracted features and labels.
arXiv Detail & Related papers (2024-04-06T16:15:02Z) - Modeling Bends in Popular Music Guitar Tablatures [49.64902130083662]
Tablature notation is widely used in popular music to transcribe and share guitar musical content.
This paper focuses on bends, which enable to progressively shift the pitch of a note, therefore circumventing physical limitations of the discrete fretted fingerboard.
Experiments are performed on a corpus of 932 lead guitar tablatures of popular music and show that a decision tree successfully predicts bend occurrences with an F1 score of 0.71 anda limited amount of false positive predictions.
arXiv Detail & Related papers (2023-08-22T07:50:58Z) - ProgGP: From GuitarPro Tablature Neural Generation To Progressive Metal
Production [0.0]
We extend this work by fine-tuning a pre-trained Transformer model on ProgGP, a custom dataset of 173 progressive metal songs.
Our model is able to generate multiple guitar, bass guitar, drums, piano and orchestral parts.
We demonstrate the value of the model by using it as a tool to create a progressive metal song, fully produced and mixed by a human metal producer.
arXiv Detail & Related papers (2023-07-11T15:19:47Z) - Simple and Controllable Music Generation [94.61958781346176]
MusicGen is a single Language Model (LM) that operates over several streams of compressed discrete music representation, i.e., tokens.
Unlike prior work, MusicGen is comprised of a single-stage transformer LM together with efficient token interleaving patterns.
arXiv Detail & Related papers (2023-06-08T15:31:05Z) - GETMusic: Generating Any Music Tracks with a Unified Representation and
Diffusion Framework [58.64512825534638]
Symbolic music generation aims to create musical notes, which can help users compose music.
We introduce a framework known as GETMusic, with GET'' standing for GEnerate music Tracks''
GETScore represents musical notes as tokens and organizes tokens in a 2D structure, with tracks stacked vertically and progressing horizontally over time.
Our proposed representation, coupled with the non-autoregressive generative model, empowers GETMusic to generate music with any arbitrary source-target track combinations.
arXiv Detail & Related papers (2023-05-18T09:53:23Z) - GTR-CTRL: Instrument and Genre Conditioning for Guitar-Focused Music
Generation with Transformers [14.025337055088102]
We use the DadaGP dataset for guitar tab music generation, a corpus of over 26k songs in GuitarPro and token formats.
We introduce methods to condition a Transformer-XL deep learning model to generate guitar tabs based on desired instrumentation and genre.
Results indicate that the GTR-CTRL methods provide more flexibility and control for guitar-focused symbolic music generation than an unconditioned model.
arXiv Detail & Related papers (2023-02-10T17:43:03Z) - Melody transcription via generative pre-training [86.08508957229348]
Key challenge in melody transcription is building methods which can handle broad audio containing any number of instrument ensembles and musical styles.
To confront this challenge, we leverage representations from Jukebox (Dhariwal et al. 2020), a generative model of broad music audio.
We derive a new dataset containing $50$ hours of melody transcriptions from crowdsourced annotations of broad music.
arXiv Detail & Related papers (2022-12-04T18:09:23Z) - A Dataset for Greek Traditional and Folk Music: Lyra [69.07390994897443]
This paper presents a dataset for Greek Traditional and Folk music that includes 1570 pieces, summing in around 80 hours of data.
The dataset incorporates YouTube timestamped links for retrieving audio and video, along with rich metadata information with regards to instrumentation, geography and genre.
arXiv Detail & Related papers (2022-11-21T14:15:43Z) - POP909: A Pop-song Dataset for Music Arrangement Generation [10.0454303747519]
We propose POP909, a dataset which contains multiple versions of the piano arrangements of 909 popular songs created by professional musicians.
The main body of the dataset contains the vocal melody, the lead instrument melody, and the piano accompaniment for each song in MIDI format, which are aligned to the original audio files.
We provide the annotations of tempo, beat, key, and chords, where the tempo curves are hand-labeled and others are done by MIR algorithms.
arXiv Detail & Related papers (2020-08-17T08:08:14Z) - Foley Music: Learning to Generate Music from Videos [115.41099127291216]
Foley Music is 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 present a Graph$-$Transformer framework that can accurately predict MIDI event sequences in accordance with the body movements.
arXiv Detail & Related papers (2020-07-21T17:59:06Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.