# Impact of time and note duration tokenizations on deep learning symbolic music modeling

arXiv: https://arxiv.org/abs/2310.08497 · HTML: https://mlsanity.com/paper/2310.08497/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 46 references that are in the map.
- First posted on arXiv 12 Oct 2023.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Estimating the intrinsic dimension of datasets by a minimal neighborhood information](https://mlsanity.com/paper/1803.06992/) (2018)
- [Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs](https://mlsanity.com/paper/2101.02402/) (2021)
- [DeepBach: a Steerable Model for Bach Chorales Generation](https://mlsanity.com/paper/1612.01010/) (2016)
- [MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training](https://mlsanity.com/paper/2106.05630/) (2021)
- [POP909: A Pop-song Dataset for Music Arrangement Generation](https://mlsanity.com/paper/2008.07142/) (2020)
- [MT3: Multi-Task Multitrack Music Transcription](https://mlsanity.com/paper/2111.03017/) (2021)
- [This Time with Feeling: Learning Expressive Musical Performance](https://mlsanity.com/paper/1808.03715/) (2018)
- [PopMAG: Pop Music Accompaniment Generation](https://mlsanity.com/paper/2008.07703/) (2020)
- [Scikit-dimension: a Python package for intrinsic dimension estimation](https://mlsanity.com/paper/2109.02596/) (2021)
- [LakhNES: Improving multi-instrumental music generation with cross-domain pre-training](https://mlsanity.com/paper/1907.04868/) (2019)
- [EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation](https://mlsanity.com/paper/2108.01374/) (2021)
- [MMM : Exploring Conditional Multi-Track Music Generation with the Transformer](https://mlsanity.com/paper/2008.06048/) (2020)
- [Sequence-to-Sequence Piano Transcription with Transformers](https://mlsanity.com/paper/2107.09142/) (2021)
- [GiantMIDI-Piano: A large-scale MIDI dataset for classical piano music](https://mlsanity.com/paper/2010.07061/) (2020)
- [Symphony Generation with Permutation Invariant Language Model](https://mlsanity.com/paper/2205.05448/) (2022)
- [Multitrack Music Transformer](https://mlsanity.com/paper/2207.06983/) (2022)
- [Learning to Remove: Towards Isotropic Pre-trained BERT Embedding](https://mlsanity.com/paper/2104.05274/) (2021)
- [The Piano Inpainting Application](https://mlsanity.com/paper/2107.05944/) (2021)
- [A Survey for Efficient Open Domain Question Answering](https://mlsanity.com/paper/2211.07886/) (2022)
- [Estimating the effective dimension of large biological datasets using Fisher separability analysis](https://mlsanity.com/paper/1901.06328/) (2019)

## Built on by (most cited first, 6 of 6)

- [Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey](https://mlsanity.com/paper/2402.17467/) (2024)
- [Moonbeam: A MIDI Foundation Model Using Both Absolute and Relative Music Attributes](https://mlsanity.com/paper/2505.15559/) (2025)
- [On the de-duplication of the Lakh MIDI dataset](https://mlsanity.com/paper/2509.16662/) (2025)
- [Do we need more complex representations for structure? A comparison of note duration representation for Music Transformers](https://mlsanity.com/paper/2410.10515/) (2024)
- [MidiTok Visualizer: a tool for visualization and analysis of tokenized MIDI symbolic music](https://mlsanity.com/paper/2410.20518/) (2024)
- [How Far Should Tokenization Go? Predictive Effectiveness and Relational Losslessness](https://mlsanity.com/paper/2608.18025/) (2026)

## Abstract (arXiv)

Symbolic music is widely used in various deep learning tasks, including generation, transcription, synthesis, and Music Information Retrieval (MIR). It is mostly employed with discrete models like Transformers, which require music to be tokenized, i.e., formatted into sequences of distinct elements called tokens. Tokenization can be performed in different ways. As Transformer can struggle at reasoning, but capture more easily explicit information, it is important to study how the way the information is represented for such model impact their performances. In this work, we analyze the common tokenization methods and experiment with time and note duration representations. We compare the performances of these two impactful criteria on several tasks, including composer and emotion classification, music generation, and sequence representation learning. We demonstrate that explicit information leads to better results depending on the task.