The ISMIR conference is the world’s leading research forum on processing, searching, organizing, and accessing music-related data. At this year’s ISMIR (https://ismir2023.ismir.net/), MTG researchers are presenting quite a number of research results. Papers:

• Miguel Perez Fernandez, Holger Kirchhoff, Xavier Serra. TriAD: Capturing harmonics with 3D Convolutions. VIDEO: https://youtu.be/0RTehYN6Ed8
• Behzad Haki, Błażej Kotowski, Cheuk Lun Isaac Lee, Sergi Jordà. TapTamDrum: A Dataset for Dualized Drum Patterns. VIDEO: https://youtu.be/akLg8C5gG2g
• Carlos Penarrubia, Carlos Garrido-Munoz, Jose J. Valero-Mas, Jorge Calvo-Zaragoza. Efficient Notation Assembly in Optical Music Recognition. 
• Alia Morsi, Kana Tatsumi, Akira Maezawa, Takuya Fujishima, Xavier Serra. Sounds out of place? Score independent detection of conspicouous mistakes in piano performances. VIDEO: https://youtu.be/NiuW_6KoL1w
• Genís Plaja-Roglans, Marius Miron, Adithi Shankar, Xavier Serra. Carnatic Singing Voice Separation Using Cold Diffusion on Training Data with Bleeding. 
• Pedro Ramoneda, Dasaem Jeong, Jose J. Valero-Mas, Xavier Serra. Predicting performance difficulty from piano sheet music images. 
• Nazif Can Tamer, Yigitcan Özer, Meinard Müller, Xavier Serra. High-Resolution Violin Transcription using Weak Labels. VIDEO: https://youtu.be/REI3qkHDbpQ
• Pablo Alonso-Jiménez, Xavier Serra, Dmitry Bogdanov. Efficient Supervised Training of Audio Transformers for Music Representation Learning. VIDEO: https://youtu.be/KLjpHx6ccKc

Apart from the research presentations, Roser Batlle-Roca, Emilia Gómez and Lorenzo Porcaro are organizing, as a satellite event, the Workshop on Human-Centric Music Information Research (HCMIR), on November 10th.