blog | Maciek Tomczak

I invite you to check out what I've been up to

Virtuoso Strings Dataset

I lead the curation of the Virtuoso Strings, a dataset for timing analysis and automatic music transcription (AMT) tasks requiring note onset annotations. This dataset takes advantage of real-world recordings in multitrack format and is curated as a component of the Augmented Reality Music Ensemble (ARME) project. For ISMIR late-breaking demo, please see ismir2023program.ismir.net/lbd_312.html

1 min read · November 10, 2023

2023 · data
Singing Voice Decomposition

Audio examples accompanying an unpublished paper titled Investigating Information Bottleneck in Variational Autoencoder-based Singing Voice Decomposition which I worked on with Kin Wah Edward Lin (AIST), Tomoyasu Nakano (AIST), Jason Hockman (BCU), and Masataka Goto (AIST)

8 min read · September 14, 2021

2021 · ML
Drum Synthesis and Rhythmic Transformation with Adversarial Autoencoders

Audio examples accompanying paper for ACM International Conference on Multimedia (ACM MM) 2020.

3 min read · July 1, 2020

2020 · redrumming ML
Drum Translation for Timbral and Rhythmic Transformation

Results supplementing the paper for the International Conference on Digital Audio Effects (DAFx) 2019.

6 min read · April 12, 2019

2019 · wavenet redrumming ML
Audio Style Transfer with Rhythmic Constraints

Results supplementing the paper for the International Conference on Digital Audio Effects (DAFx) 2018.

11 min read · April 16, 2018

2018 · audio-style-transfer redrumming ML