MuTecEn

Anna-Maria

Multimodal Music Processing

[UniOslo_RITMO @UniOslo_RITMO]

Attention systematic musicology students! 🎵🔬

As 2024 draws to a close, we, the SysMus25 elves, have an important reminder:
🗓 Abstract submission deadline: January 10th, 2025

[UniOslo_RITMO @UniOslo_RITMO]

Calling all MA and PhD students of Systematic Musicology: Are you wanting to share your research with peers at the #SysMus25 conference hosted by RITMO at the University of Oslo on the 11-13th of June 2025? Well, you are in luck!

[Jonathan Cannon @joncannon_neuro]

@UniOslo_RITMO is recruiting a PhD student to study musical microrhythm, supervised by @annedanielsen and Rainer Polack. This is the best imaginable situation for a budding rhythm nerd. If you have any star undergrads in your lab open to a move to Norway...https://t.co/mMRuQiXB90

[MuTecEn @MuTecEn]

Our new paper "Multimodal music datasets? Challenges and future goals in music processing" is out!

We define "multimodality" in music, and tackle dataset challenges.

Link: https://t.co/dizGydMmSr

@RITMO @alexarje @OlliLartinen

[MuTecEn @MuTecEn]

Art.

[MuTecEn @MuTecEn]

@dorienherremans I think there are many things to work on/improve, even though it feels like new advancements are "small" and too specific. Listening to the musicians, educators, students, users etc would give us a nice idea of what works or not and what is needed

[Dorien Herremans @dorienherremans]

What should we work on in music AI? Should we compose a similar document?

[UniOslo_RITMO @UniOslo_RITMO]

We have no less than THREE new positions at RITMO!🎉
Two Doctoral Research Fellowships and one Postdoctoral Research Fellow.
Deadline February 1.
See below for more info!
https://t.co/wAO6UqEFA6

[lyra @_lyraaaa_]

be careful which library you're using to load large numbers of audio files. librosa and pydub are very slow. the others are good. audioread is *very* fast.

[EnginyEria - UPF @enginyeria_upf]

📖#NewBook! 'Neurocognitive Music Therapy' by Dr. Rafael Ramírez-Meléndez from @mtg_upf

🗣️"The book provides an overview of neurocognitive music therapy, its impact and implications in the practice of evidence-based music interventions"

https://t.co/v2sW1T62gQ

[Alexander Chen @alexanderchen]

"Guess the song title based on my drawing ..."🎄🎵 #Google #Gemini

[Riccardo Fosco Gramaccioni @riccardofosco]

Truly proud of this work done with @marcomunita and @EmilianPostola1! Check it out!
Also thanks to our respective advisors @dhan90001 @IntelSoundEng @EmanueleRodola

[Mirage @MirageUIO]

Recent publication by Hans-Hinrich Thedens and @OlliLartinen: "AudioSegmentor: Et verktøy for formidling av arkivopptak på nettet" (AudioSegmentor: A tool for disseminating archival recordings online)
https://t.co/OQ4fKan7d9

[Ethan Manilow @ethanmanilow]

Next year I'll be hosting a Student Researcher on the Magenta Team at @GoogleDeepMind who's primary goal will be to explore new methods for controllable generative models for music.

Apply at the link below (US only) and reach out with any questions.

https://t.co/BdiR4Ynixs

[MuTecEn @MuTecEn]

Very interesting new MULTIMODAL model from Google to "enhance creativity, extend knowledge, advance science and transform the way billions of people live and work around the world".

[Google @Google]

We believe in making AI helpful for everyone. That’s why we’re launching Gemini, our most capable model that’s inspired by the way people understand and interact with the world. #GeminiAI

[Julian Lenz @JLenzyy]

Every leading AI x Music company should have at least one senior-level member who spent a portion of their life as a *professional* musician.

Groups composed solely of engineers simply cannot understand the immensely difficult life of a 21st century working artist.

[MIRtoolbox @mirtoolbox]

Hi! Since the MIRtoolbox official webpage has been currently removed, we just released MIRtoolbox GitHub project. You can download the latest version from here.
https://t.co/qQSgA9rQhw

[Minz Won @MinzWon]

I'm excited to introduce our new foundation model for music audio, demonstrating remarkable performance gain in multiple downstream tasks, even with shallow probing layers. The pretrained model is available online. 🎶

Paper: https://t.co/4IX9BfwvXm
Code: https://t.co/eZLQUYXtzp

[Magdalena Fuentes @mfu3ntes]

🔊🎶mirdata 0.3.8 is out‼️ 7 new loaders, for a total of 52 dataset loaders! If you work in MIR and haven’t checked it out yet, now is your chance! #@ISMIRConf

Zenodo: https://t.co/ZfDF2t7t0f
Datasets: https://t.co/x4VnmxOlNa

[Pablo Alonso Jiménez @pablo__alonso]

✍️New model out✍️

MAEST is an open music representation model trained in music style classification.

🎙️Conf: Accepted in #ISMIR2023
📄Paper: https://t.co/Fk0967Pkrf
💻Code: https://t.co/sGyPfd5sby
⚙️Essentia: https://t.co/N1cG4D0Rr4
🤗 HF: https://t.co/5EE33CWSiv

🧵👇 [1/6]