mlsanityData to 14 Oct 2026

Analyzing Byte-Pair Encoding on Monophonic and Polyphonic Symbolic Music: A Focus on Musical Phrase Segmentation

arXiv 2410.01448 ↗First posted 2 Oct 2024cs.IR cs.CL cs.SDcited by 0

Not on the map. Why?

Abstract (arXiv)

Byte-Pair Encoding (BPE) is an algorithm commonly used in Natural Language Processing to build a vocabulary of subwords, which has been recently applied to symbolic music. Given that symbolic music can differ significantly from text, particularly with polyphony, we investigate how BPE behaves with different types of musical content. This study provides a qualitative analysis of BPE's behavior across various instrumentations and evaluates its impact on a musical phrase segmentation task for both monophonic and polyphonic music. Our findings show that the BPE training process is highly dependent on the instrumentation and that BPE "supertokens" succeed in capturing abstract musical content. In a musical phrase segmentation task, BPE notably improves performance in a polyphonic setting, but enhances performance in monophonic tunes only within a specific range of BPE merges.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 31 references that are in the map. First posted on arXiv 2 Oct 2024.

Builds on

14 of 31 references.

References · 14

  1. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  2. 2018XNLI: Evaluating Cross-lingual Sentence Representationscited by 915
  3. 2018Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidatescited by 639
  4. 2021Charformer: Fast Character Transformers via Gradient-based Subword Tokenizationcited by 160
  5. 2023miditok: A Python package for MIDI file tokenizationcited by 27
  6. 2021The Piano Inpainting Applicationcited by 23
  7. 2021AccoMontage: Accompaniment Arrangement via Phrase Selection and Style Transfercited by 22
  8. 2016A Character-Level Decoder without Explicit Segmentation for Neural Machine Translationcited by 21
  9. 2023Byte Pair Encoding for Symbolic Musiccited by 19
  10. 2023Symbolic Music Representations for Classification Tasks: A Systematic Evaluationcited by 14
  11. 2024Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Surveycited by 10
  12. 2018Melodic Phrase Segmentation By Deep Neural Networkscited by 6
2 more
  1. 2018BPE and CharCNNs for Translation of Morphology: A Cross-Lingual Comparison and Analysiscited by 4
  2. 2023From Words to Music: A Study of Subword Tokenization Techniques in Symbolic Music Generationcited by 2

Built on by

Not cited yet.